Search

Sales managers are unlikely to reap the benefits of implementing predictive analytics applications when salespeople show aversion to or lack understanding of these applications. For managers, it is essential to understand which factors mitigate or exacerbate these challenges. This article investigates these factors by studying the implementation of an application that predicts customer churn. Using 9.7 million transactions from a business-to-business company, the authors develop a predictive model of customer churn, implement it in a field experiment, and study its treatment effects using causal forests. Furthermore, the authors manipulate one specific mitigation strategy proposed by prior literature: the fostering of users' realistic expectations regarding the accuracy of an algorithm. The results show that the effectiveness of the churn prediction application strongly depends on customer characteristics (most importantly the predicted churn probability and prior revenue) and salesperson characteristics (technology perceptions, abilities, and selling orientations). Fostering realistic expectations improves the effectiveness of the churn prediction only under very specific circumstances. Two follow-up stimuli-based experiments conceptually replicate key results of the field study. Therefore, this article helps build theory on predictive sales analytics and provides specific guidance to managers aiming to increase their return on analytics investments. [ABSTRACT FROM AUTHOR]

The competition among Food & Beverage companies has substantially increased in today's age of digitization. Sales forecasting is one of their main challenges. Due to space limitations, employee shortages, and rising online demand, retail sales forecasting became extremely important for Food and Beverage companies. This research analyzed the sales data of a multinational Food & Beverage Company. It proposed a framework using Gaussian Mixture Model (GMM) clustering, Hierarchical Agglomerative Clustering (HAC), and Random Forest algorithm for forecasting sales. This model analyzes the impact of the weekends, holidays, promotional activities, customer sentiments, festivals, and socio-economic situations in sales data and is able to forecast sales ranging from one to 15 months. An investigation of the suggested model's performance compared to numerous cutting-edge sales forecasting techniques is carried out to show its efficacy. Here, we demonstrate that the proposed hybrid model surpasses current predicting and computing efficiency methods. The results of this study can help retail managers to allocate resources and manage inventories in well-informed ways. The findings suggest that combining many strategies may produce the most precise forecasts. [ABSTRACT FROM AUTHOR]

The article "Addressing Bias in Pharmaceutical Pipeline Forecasting" by Richard Murgatroyd discusses the unique challenges in forecasting sales revenues for new pharmaceutical products. The pharmaceutical industry faces high development risks, patent protection issues, and post-patent generic substitution. Forecasting methods are often subjective and influenced by organizational politics, leading to potential bias and manipulation. To mitigate these issues, the author proposes a peer review process for forecasts and emphasizes the importance of transparency and objectivity in forecasting practices. [Extracted from the article]

Sales forecasting is one of the critical areas in business analytics where business organizations aim to enhance efficiency and, therefore, revenues. An excellent example of a CRM program is Salesforce, which produces massive amounts of sales data that are essential for forecasting and decision-making. Data analysis involves the use of complex and effective tools for its processing. This study proposes a framework based on the following classification algorithms: Support Vector Machines (SVM), Decision Trees (DT), and Random Forests (RF). The proposed framework follows a fine-tuned approach to improve the prediction of sales data. Regarding the fine-tuning of these algorithms, it was observed that specific changes were required within the hyperparameters to better relate to the inherent patterns and other factors that exist in the sales data. The optimization process was very crucial in improving the performance of the model. The proposed framework was used on a sales dataset and evaluated in terms of accuracy, precision, data loss, and F1 score. Fine-tuned algorithms had higher accuracy and lower data loss. [ABSTRACT FROM AUTHOR]

Forecasting refined oil sales is essential in energy supply chain management. However, accurate forecasting is limited by several factors, including multiple influences of external features, heterogeneity of different gasoline stations, and difficulty in balancing linear and nonlinear forecasting. To address these issues, we propose a novel variable‐weight combined forecasting model. In the first stage, the model incorporates causal analysis and clustering methods to provide a quantitative description of multiple effects of external features and highly correlated aggregation of homogeneous data. Subsequently, based on the patterns of external feature influences learned from historical data, variable‐weight combined forecasting is realized to balance linear and nonlinear forecasting dynamically. Experiments based on real sales data procured from several regions demonstrate that the proposed model outperforms other benchmark and widely used models in terms of forecasting accuracy and statistical significance. The ablation experimental results confirm the significance of causal analysis, clustering, and variable‐weight combined forecasting in improving the balance between linear and nonlinear forecasting. Moreover, our results indicate that improving the quality of clustering can yield greater benefits than improving the amount of training data. Finally, we also explore whether the forecasting superiority translates into better inventory control, and our results show that the proposed optimization model can effectively balance inventory cost and service level, while also better suppress the bullwhip effect. [ABSTRACT FROM AUTHOR]

Aiming to address the complexity and challenges of predicting pure electric vehicle (EV) sales, this paper integrates a time series model, support vector machine and combined model to forecast EV sales in China. Firstly, a seasonal autoregressive integrated moving average (SARIMA) model was constructed using historical EV sales data, and the model was trained on sales statistics to obtain forecasting results. Secondly, variables that were highly correlated with sales were analyzed using gray relational analysis (GRA) and utilized as input parameters for the support vector regression (SVR) model, which was constructed to optimize sales predictions for EVs. Finally, a combined model incorporating different algorithms was verified against market sales data to explore the optimal sales prediction approach. The results indicate that the SARIMA-GRA-SVR model with the squared prediction error and inverse method achieved the best predictive performance, with MAPE, MAE and RMSE values of 12%, 1.45 and 2.08, respectively. This empirical study validates the effectiveness and superiority of the SARIMA-GRA-SVR model in forecasting EV sales. [ABSTRACT FROM AUTHOR]

Sales forecasting plays an important role in business operations as it impacts decisions on inventory management, allocation of resources, and financial planning. Accurate sales predictions are essential for optimizing cash flow management, adapting marketing and sales strategies, and facilitating strategic planning. This study presents a computational framework for predicting business sales using transformers, which are considered one of the most powerful deep learning architectures. The design of our model is specifically tailored to accommodate tabular data with low dimensions. The experimental results demonstrated that our proposed method surpasses conventional machine learning models, achieving reduced mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE), as well as higher R2 values of nearly 0.95. The results confirmed that the model is applicable not only to this research but also to similar studies that use low-dimensional tabular data. The improved accuracy and stability of our model demonstrate its potential as a useful tool for enhancing sales prediction, therefore facilitating more informed decision-making and strategic planning in corporate operations. [ABSTRACT FROM AUTHOR]

Forecasting sales trends is a valuable activity for companies of all types and sizes, as it enables more efficient decision making to avoid unnecessary expenses from excess inventory or, conversely, losses due to insufficient inventory to meet demand. In this paper, we designed a personalized cost function to reduce economic losses caused by the excessive acquisition of products or derived from their scarcity when needed. Moreover, we designed an LSTM network integrated with Glorot and Orthogonal initializers and dropout to forecast sales trends in a lumber mill in Tamaulipas, Mexico. To generalize and appropriately forecast the sales of the lumber mill products, we optimized the LSTM network's hyperparameters through a genetic algorithm, which was essential to explore the solution space. We evaluated our proposal in instances obtained from the historical sales of the five main products sold by the lumber mill. According to the results, we concluded that for our case study the proposed function cost and the hyperparameters optimization allowed the LSTM to forecast the direction and trend of the lumber mill's product sales despite the variability of the products. [ABSTRACT FROM AUTHOR]

Dijital dönüşüm ile tedarik zinciri yönetiminde büyük veri analitiğinin önemi gün geçtikçe artmaktadır. Özellikle müşteri taleplerinin hızlı ve doğru tahmin edilmesinde büyük verinin kullanımı firmalara rekabet avantajı sağlamaktadır. Bu doğrultuda, yapay zekâ tekniklerinden biri olan derin öğrenme modelleri büyük verideki karmaşık örüntülerin keşfedilmesinde öne çıkmaktadır. Son yıllarda literatürde çok sayıda derin öğrenme yöntemi önerilmiştir. Bu çalışmada, satış tahmini problemi için derin öğrenme yöntemlerinin performansları karşılaştırılmıştır. Bu kapsamda derin sinir ağı (DNN), derin otokodlayıcı (Deep AE), evrişimli sinir ağı (CNN), tekrarlayan sinir ağı (RNN), uzun kısa-süreli bellek (LSTM) ağı, çift yönlü LSTM (Bi-LSTM) ağı, kapılı tekrarlayan birim (GRU), CNN-LSTM ve evrişimli LSTM (ConvLSTM) yöntemleri uygulanmıştır. Çeşitli sektörlere ait satış verileri kullanılarak deneysel çalışmalar gerçekleştirilmiştir. Hiperparametre optimizasyonu ardından ele alınan yöntemlerin performansları tahmin doğruluğu ve eğitim süreleri açısından karşılaştırılarak sonuçların istatistiksel anlamlılığı değerlendirilmiştir. Sonuç olarak, LSTM ve GRU modellerinin tahmin doğruluğunda başarılı sonuçlar verdiği, CNN modelinin ise eğitim süresini kısalttığı görülmüştür.

This study explores the synergies between marketing strategies, analytical insights, and consumer education in propelling electric vehicle (EV) adoption. We uncover intricate sales patterns in Türkiye's EV sales data using advanced statistical models such as Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), and Error, Trend, and Seasonality (ETS). Türkiye's fully electric vehicle (FEV) sales value was estimated in the next five-year period using the ARIMA (4,1,4) model. According to the research results, the FEV sales rate in Türkiye is expected to increase by an average value of 58.2% in the next five-year period, and the annual sales amount, excluding Tesla, will be 17459. Findings underscore the efficacy of aligning marketing strategies with analytical insights, demonstrating the significance of education in shaping positive consumer attitudes. Education-driven marketing emphasizing economic benefits, reduced emissions, and technological advancements is a potent catalyst in overcoming adoption barriers. Digital campaigns, experiential marketing, and sustainability messaging, validated by our analysis, play pivotal roles in influencing consumer behavior. Strategic partnerships with energy companies address infrastructure challenges, while incentive-based marketing, personalized strategies, and after-sales support foster a sense of community and loyalty. This research contributes a holistic framework for marketers, policymakers, and stakeholders to navigate the evolving landscape of EV adoption successfully, providing actionable insights and paving the way for future research directions in sustainable transportation. [ABSTRACT FROM AUTHOR]

Motivated by our collaboration with Anheuser-Busch InBev (AB InBev), a consumer packaged goods (CPG) company, we consider the problem of forecasting sales under the coronavirus disease 2019 (COVID-19) pandemic. Our approach combines nonparametric regression, game theory, and pandemic modeling to develop a data-driven competitive online nonparametric regression method. Specifically, the method takes the future COVID-19 case estimates, which can be simulated via the susceptible-infectious-removed (SIR) epidemic model as an input, and outputs the level of calibration for the baseline sales forecast generated by AB InBev. In generating the calibration level, we focus on an online learning setting where our algorithm sequentially predicts the label (i.e., the level of calibration) of a random covariate (i.e., the current number of active cases) given past observations and the generative process (i.e., the SIR epidemic model) of future covariates. To provide robust performance guarantee, we derive our algorithm by minimizing regret, which is the difference between the squared ℓ2 -norm associated with labels generated by the algorithm and labels generated by an adversary and the squared ℓ2 -norm associated with labels generated by the best isotonic (nondecreasing) function in hindsight and the adversarial labels. We develop a computationally efficient algorithm that attains the minimax-optimal regret over all possible choices of the labels (possibly non-i.i.d. and even adversarial). We demonstrate the performances of our algorithm on both synthetic and AB InBev's data sets of three different markets (each corresponds to a country) from March 2020 to March 2021. The AB InBev's numerical experiments show that our method is capable of reducing the forecast error in terms of weighted mean absolute percentage error (WMAPE) and mean squared error (MSE) by more than 37% for the company. This paper was accepted by J. George Shanthikumar, data science. Funding: This work was partially supported by the Massachusetts Institute of Technology Data Science Lab and AB-InBev Corporation. Supplemental Material: The e-companion and data are available at https://doi.org/10.1287/mnsc.2023.4969. [ABSTRACT FROM AUTHOR]

Customized production has greatly diversified product categories, which has altered product life cycles and added complexity to business management. This paper introduces a matrix-clustering technique that integrates k-means clustering with the BCG Matrix, enhanced by time modeling, to offer a comprehensive framework for multi-item product sales forecasting. The approach builds upon existing BCG Matrix outcomes, re-clustering high-selling products more precisely and redefining their relationship with other product lines more objectively. This method addresses the challenge of forecasting situations with limited historical data, providing more accurate sales predictions. Using Taiwan's sales data, an empirical study on integrated circuit tray products demonstrated the effectiveness of the matrix clustering technique. The results showed improved data utilization, increasing from 35.93% with the original BCG analysis to 52.43% with the combined matrix-clustering and time modeling methods. This study contributes to academic research by presenting a portfolio analysis approach rooted in matrix clustering, which systematically enhances traditional BCG Matrix methods. The proposed framework is adaptable to the unique traits of different portfolios, offering businesses workflows that are efficient, reliable, sustainable, and scalable. [ABSTRACT FROM AUTHOR]

Short-cycle agricultural product sales forecasting significantly reduces food waste by accurately predicting demand, ensuring producers match supply with consumer needs. However, the forecasting is often subject to uncertain factors, resulting in highly volatile and discontinuous data. To address this, a hierarchical prediction model that combines RF-XGBoost is proposed in this work. It adopts the Random Forest (RF) in the first layer to extract residuals and achieve initial prediction results based on correlation features from Grey Relation Analysis (GRA). Then, a new feature set based on residual clustering features is generated after the hierarchical clustering is applied to classify the characteristics of the residuals. Subsequently, Extreme Gradient Boosting (XGBoost) acts as the second layer that utilizes those residual clustering features to yield the prediction results. The final prediction is by incorporating the results from the first layer and second layer correspondingly. As for the performance evaluation, using agricultural product sales data from a supermarket in China from 1 July 2020 to 30 June 2023, the results demonstrate superiority over standalone RF and XGBoost, with a Mean Absolute Percentage Error (MAPE) reduction of 10% and 12%, respectively, and a coefficient of determination (R2) increase of 22% and 24%, respectively. Additionally, its generalization is validated across 42 types of agricultural products from six vegetable categories, showing its extensive practical ability. Such performances reveal that the proposed model beneficially enhances the precision of short-term agricultural product sales forecasting, with the advantages of optimizing the supply chain from producers to consumers and minimizing food waste accordingly. [ABSTRACT FROM AUTHOR]

Although live streaming is indispensable, live-streaming e-business requires accurate and timely sales-volume prediction to ensure a healthy supply–demand balance for companies. Practically, because various factors can significantly impact sales results, the development of a powerful, interpretable model is crucial for accurate sales prediction. In this study, we propose SaleNet, a deep-learning model designed for sales-volume prediction. Our model achieved correct prediction results on our private, real operating data. The mean absolute percentage error (MAPE) of our model's performance fell as low as 11.47% for a + 1.5-days forecast. Even for a 1-week forecast (+ 6 days), the MAPE was only 19.79%, meeting actual business needs and practical requirements. Notably, our model demonstrated robust interpretability, as evidenced by the feature contribution results which are consistent with prevailing research findings and industry expertise. Our findings provided a theoretical foundation for predicting shopping behavior in live-broadcast e-commerce and offered valuable insights for designing live-broadcast content and optimizing the user experience. [ABSTRACT FROM AUTHOR]

In a dynamic environment characterized by rapid market competition and unanticipated changes, supply chains emphasize the cost-effective implementation of responsive strategies. Moreover, enterprises are experiencing the repercussions of substantial economic transformations precipitated by the COVID-19 pandemic. This research paper aims to identify the critical enablers of responsiveness in Vietnam's jewelry supply chain and rank the supply chain responsiveness (SCR) areas. Evaluating and developing in a challenging economic context is essential to support top management in reallocating resources based on a more empirical foundation. This article presents a novel integrated method combining demand forecasting, the rough Z-number, Stepwise Weight Assessment Ratio Analysis (SWARA), and TODIM (Interactive and Multi-Criteria Decision Making in Portuguese). The approach can decrease the number of pairwise comparisons substantially and demonstrate a substantial benefit in managing ambiguous data and ensuring the dependability of the assessment. [ABSTRACT FROM AUTHOR]

In a dynamic business environment, the accuracy of sales forecasts plays a pivotal role in strategic decision making and resource allocation. This article offers a systematic review of the existing literature on techniques and methodologies used in forecasting, especially in sales forecasting across various domains, aiming to provide a nuanced understanding of the field. Our study examines the literature from 2013 to 2023, identifying key techniques and their evolution over time. The methodology involves a detailed analysis of 516 articles, categorized into classical qualitative approaches, traditional statistical methods, machine learning models, deep learning techniques, and hybrid approaches. The results highlight a significant shift towards advanced methods, with machine learning and deep learning techniques experiencing an explosive increase in adoption. The popularity of these models has surged, as evidenced by a rise from 10 articles in 2013 to over 110 by 2023. This growth underscores their growing prominence and effectiveness in handling complex time series data. Additionally, we explore the challenges and limitations that influence forecasting accuracy, focusing on complex market structures and the benefits of extensive data availability. [ABSTRACT FROM AUTHOR]

In the present scenario, retail sales forecasting has a great significance in E-commerce companies. The precise retail sales forecasting enhances the business decision making, storage management, and product sales. Inaccurate retail sales forecasting can decrease customer satisfaction, inventory shortages, product backlog, and unsatisfied customer demands. In order to obtain a better retail sales forecasting, deep learning models are preferred. In this manuscript, an effective Bi-GRU is proposed for accurate sales forecasting related to E-commerce companies. Initially, retail sales data are acquired from two benchmark online datasets: Rossmann dataset and Walmart dataset. From the acquired datasets, the unreliable samples are eliminated by interpolating missing data, outlier's removal, normalization, and de-normalization. Then, feature engineering is carried out by implementing the Adaptive Particle Swarm Optimization (APSO) algorithm, Recursive Feature Elimination (RFE) technique, and Minimum Redundancy Maximum Relevance (MRMR) technique. Followed by that, the optimized active features from feature engineering are given to the Bi-Directional Gated Recurrent Unit (Bi-GRU) model for precise retail sales forecasting. From the result analysis, it is seen that the proposed Bi-GRU model achieves higher results in terms of an R2 value of 0.98 and 0.99, a Mean Absolute Error (MAE) of 0.05 and 0.07, and a Mean Square Error (MSE) of 0.04 and 0.03 on the Rossmann and Walmart datasets. The proposed method supports the retail sales forecasting by achieving superior results over the conventional models. [ABSTRACT FROM AUTHOR]

New fashion product sales forecasting is a challenging problem that involves many business dynamics and cannot be solved by classical forecasting approaches. In this paper, we investigate the effectiveness of systematically probing exogenous knowledge in the form of Google Trends time series and combining it with multi‐modal information related to a brand‐new fashion item, in order to effectively forecast its sales despite the lack of past data. In particular, we propose a neural network‐based approach, where an encoder learns a representation of the exogenous time series, while the decoder forecasts the sales based on the Google Trends encoding and the available visual and metadata information. Our model works in a non‐autoregressive manner, avoiding the compounding effect of large first‐step errors. As a second contribution, we present VISUELLE, a publicly available dataset for the task of new fashion product sales forecasting, containing multimodal information for 5,577 real, new products sold between 2016 and 2019 from Nunalie, an Italian fast‐fashion company. The dataset is equipped with images of products, metadata, related sales, and associated Google Trends. We use VISUELLE to compare our approach against state‐of‐the‐art alternatives and several baselines, showing that our neural network‐based approach is the most accurate in terms of both percentage and absolute error. It is worth noting that the addition of exogenous knowledge boosts the forecasting accuracy by 1.5% in terms of Weighted Absolute Percentage Error (WAPE), revealing the importance of exploiting informative external information. The code and dataset are both available online (at https://github.com/HumaticsLAB/GTM-Transformer). [ABSTRACT FROM AUTHOR]

In recent years, machine learning models based on big data have been introduced into marketing in order to transform customer data into meaningful insights and to make strategic decisions by making more accurate predictions. Although there is a large amount of literature on demand forecasting, there is a lack of research about how marketing strategies such as advertising and other promotional activities affect demand. Therefore, an accurate demand-forecasting model can make significant academic and practical contributions for business sustainability. The purpose of this article is to evaluate machine learning methods to provide accuracy in forecasting demand based on advertising expenses. The study focuses on a prediction mechanism based on several Machine Learning techniques—Support Vector Regression (SVR), Random Forest Regression (RFR) and Decision Tree Regressor (DTR) and deep learning techniques—Artificial Neural Network (ANN), Long Short Term Memory (LSTM),—to deal with demand forecasting based on advertising expenses. Deep learning is a powerful technique that can solve marketing problems based on both classification and regression algorithms. Accordingly, a television manufacturer's real market dataset consisting of advertising expenditures, sales and demand forecasting via chosen machine learning methods was analyzed and compared in terms of the accuracy of demand forecasting. As a result, Long Short Term Memory has been found to be superior to other models in providing highly accurate prediction results for demand forecasting based on advertising expenses. [ABSTRACT FROM AUTHOR]

Existing sales forecasting models are not comprehensive and flexible enough to consider dynamic changes and nonlinearities in sales time-series at the store and product levels. To capture different big data characteristics in sales forecasting data, such as seasonal and trend variations, this study develops a hybrid model combining adaptive trend estimated series (ATES) with a deep neural network model. ATES is first used to model seasonal effects and incorporate holiday, weekend, and marketing effects on sales. The deep neural network model is then proposed to model residuals by capturing complex high-level spatiotemporal features from the data. The proposed hybrid model is equipped with a feature-extraction component that automatically detects the patterns and trends in time-series, which makes the forecasting model robust against noise and time-series length. To validate the proposed hybrid model, a large volume of sales data is processed with a three-dimensional data model to effectively support business decisions at the product-specific store level. To demonstrate the effectiveness of the proposed model, a comparative analysis is performed with several state-of-the-art sales forecasting methods. Here, we show that the proposed hybrid model outperforms existing models for forecasting horizons ranging from one to 12 months. [ABSTRACT FROM AUTHOR]

Efficient inventory management is essential for maintaining a balance between supply and demand in various industries. This research study aims to quantitatively examine the impact of supply chain delays, with a specific emphasis on lead times and in-transit amounts, inventory levels, and the ability to meet sales demands. Mathematical modeling and statistical analysis are utilized to create prediction models that assess the impact of variations in lead time and quantities in transit on inventory stability and fulfillment rates. The study used regression analysis to ascertain the relationships between the indicated parameters and inventory outcomes. Also, machine learning algorithms like Random Forest and Linear Regression are applied to predict possible disruptions and optimize inventory levels. The methodology followed focuses on the Tri-Model Fusion Stacking approach, which combines various models to improve the predicted accuracy and offer a more comprehensive analysis. The main goal of this research is to provide practical insights that help organizations optimize their inventory management techniques, resulting in cost reduction and enhanced service levels. The findings aim to simplify the modification of inventory management techniques in light of up-to-date supply chain information, providing a notable improvement in the resources available to supply chain experts. [ABSTRACT FROM AUTHOR]

Deep learning (DL) has been widely applied to forecast the sales volume of household appliances with high accuracy. Unfortunately, in small towns, due to the limited amount of historical sales data, it is difficult to forecast household appliance sales accurately. To overcome the above-mentioned challenge, we propose a novel household appliance sales forecasting algorithm based on transfer learning, temporal convolutional network (TCN), long short-term memory (LSTM), and attention mechanism (called "TransTLA"). Firstly, we combine TCN and LSTM to exploit the spatiotemporal correlation of sales data. Secondly, we utilize the attention mechanism to make full use of the features of sales data. Finally, in order to mitigate the impact of data scarcity and regional differences, a transfer learning technique is used to improve the predictive performance in small towns, with the help of the learning experience from the megacity. The experimental outcomes reveal that the proposed TransTLA model significantly outperforms traditional forecasting methods in predicting small town household appliance sales volumes. Specifically, TransTLA achieves an average mean absolute error (MAE) improvement of 27.60% over LSTM, 9.23% over convolutional neural networks (CNN), and 11.00% over the CNN-LSTM-Attention model across one to four step-ahead predictions. This study addresses the data scarcity problem in small town sales forecasting, helping businesses improve inventory management, enhance customer satisfaction, and contribute to a more efficient supply chain, benefiting the overall economy. [ABSTRACT FROM AUTHOR]

This study proposes novel sales forecasting approaches that merge deep learning methods in a hybrid model. Long short‐term memory (LSTM) is adopted for modeling the temporal characteristics of the data, whereas the convolutional neural network (CNN) focuses on identifying and extracting relevant exogenous information. We propose stacked (S‐CNN‐LSTM) and parallel (P‐CNN‐LSTM) hybrid architectures to understand complex time series data with varying seasonal patterns and multiple products correlations. The performance drivers of both architectures were empirically tested with a real‐world multivariate retail dataset and outperformed when compared with simple neural network architectures and standard autoregressive methods for short and long‐term forecasting horizons. When compared with traditional predictive approaches, the proposed hybrid models reduce the computational complexity while providing flexibility and robustness. [ABSTRACT FROM AUTHOR]

Sales forecasting plays an important role in business operations as it impacts decisions on inventory management, allocation of resources, and financial planning. Accurate sales predictions are essential for optimizing cash flow management, adapting marketing and sales strategies, and facilitating strategic planning. This study presents a computational framework for predicting business sales using transformers, which are considered one of the most powerful deep learning architectures. The design of our model is specifically tailored to accommodate tabular data with low dimensions. The experimental results demonstrated that our proposed method surpasses conventional machine learning models, achieving reduced mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE), as well as higher R2 values of nearly 0.95. The results confirmed that the model is applicable not only to this research but also to similar studies that use low-dimensional tabular data. The improved accuracy and stability of our model demonstrate its potential as a useful tool for enhancing sales prediction, therefore facilitating more informed decision-making and strategic planning in corporate operations.

In a dynamic business environment, the accuracy of sales forecasts plays a pivotal role in strategic decision making and resource allocation. This article offers a systematic review of the existing literature on techniques and methodologies used in forecasting, especially in sales forecasting across various domains, aiming to provide a nuanced understanding of the field. Our study examines the literature from 2013 to 2023, identifying key techniques and their evolution over time. The methodology involves a detailed analysis of 516 articles, categorized into classical qualitative approaches, traditional statistical methods, machine learning models, deep learning techniques, and hybrid approaches. The results highlight a significant shift towards advanced methods, with machine learning and deep learning techniques experiencing an explosive increase in adoption. The popularity of these models has surged, as evidenced by a rise from 10 articles in 2013 to over 110 by 2023. This growth underscores their growing prominence and effectiveness in handling complex time series data. Additionally, we explore the challenges and limitations that influence forecasting accuracy, focusing on complex market structures and the benefits of extensive data availability.

Abstract People have benefited enormously from e-commerce’s explosive expansion in recent years. E-commerce, in contrast to the traditional business environment, is dynamic and complicated, which poses a number of challenges. The prediction market can create mixed intelligence for sales forecasting, which is essential for e-commerce enterprises, to handle this difficulty. Combining the usage of human analysts and machine learning algorithms can accomplish this. To accurately anticipate retailer volume and allot resources, a novel methodology for optimizing supply chain management at CBEC is proposed in this paper. The framework improves efficiency and profitability by using fuzzy logic and auction theory to make strategic decisions. Thanks to this creative strategy, managers can now make more informed decisions, ultimately enhancing the efficiency of CBEC’s supply chain. The results of this paper reveal that our proposed method is superior to previous comparable methods, with RMSE and MAE values of 22.31 and 18.76, respectively. This approach offers a promising solution to the challenges faced by e-commerce businesses, and can help them achieve greater success in the dynamic and complex world of online commerce.

This tutorial explores the use of qualitative predictor variables in linear regression, specifically focusing on incorporating location data into multiple linear regression models using dummy variables. It addresses questions related to computation, interpretation, and the significance of qualitative variables in estimating umbrella sales. The article provides an example using rainfall and location data to estimate umbrella sales and discusses the basics of using dummy variables for qualitative predictors. It also mentions alternative computational methods and transformations that can be used to improve the fit of the models, emphasizing the importance of effectively combining quantitative and qualitative data and using statistical models with caution. [Extracted from the article]

This article provides an overview of the importance of evaluating forecasts and the current state of evaluating point forecasts. The main goal of evaluation is to monitor and improve the forecasting process. The article highlights the need to select the appropriate error measure, such as root mean squared error (RMSE), when evaluating forecasts. It also discusses the importance of scaling error measures when evaluating forecasts across different aggregations. The article suggests alternative approaches to the commonly used mean absolute percentage error (MAPE) and introduces concepts like root mean squared scaled error (RMSSE) and relative RMSE (rRMSE) for scaling error measures. Additionally, the article introduces the concept of forecast value added (FVA) as a way to compare different forecasting approaches. The author emphasizes the importance of accurately measuring and interpreting error measures in forecast evaluation. [Extracted from the article]

This research uses difference-in-difference (DID) and other empirical methods to analyze firm-level real estate data to discover how heterogeneous firm characteristics affect managers' decision-making about development expansion when a firm faces a temporary negative sales shock in the Chinese housing market. The manager's decision is a utility maximization problem under uncertainty, determined by their risk aversion levels, which managers choose to optimize by considering other factors of interest, including career risk and personal wealth. Also, the advance payment rule encourages real estate developers to maintain high turnover, since new projects allow developers to collect cash first. The results show that state-owned enterprises (SOEs) are much more conservative than other types of developers. SOEs tend to focus on current developing projects. Firms with more concentrated management pursue expansion and seek to use new project sales to compensate for their slower growth. Larger developers with headquarters in large cities tend to slow their development speed when they observe negative signals, as they can quickly engage in new projects given these firms' easy access to financial resources such as bank loans. This study makes a novel contribution to the literature since previous research has tended to focus on the macro market level rather than the firm level. The findings also have strong policy and regulation value. The results indicate that higher cashflow monitoring needs, especially to monitor family-owned developers, to prevent misuse and excessive project expansion. [ABSTRACT FROM AUTHOR]

Due to new technologies, sales forecasting has become increasingly popular as a way to improve market operations and productivity in the retail industry. Although the business has historically concentrated on a stand-ard statistical model, machine-learning techniques have garnered increased attention in recent years. A key com-ponent of retail is store sales. The most trustworthy models are scrutinized by administrators in order to help fore-cast future sales. Making decisions based on historical and present data might be facilitated by forecasting future variations or increases in store sales. By recognizing sales patterns and trends, accurate forecasting will help busi-nesses or retailers increase profitability and enhance the customer experience. Predicting retail store sales with deep learning and machine learning (ML) approaches yields high. This study summarizes ML techniques to identify the best algorithm for predicting retail sales based on a collection of prior research articles. This work detects the most influencing attributes that affect sales, and suitable ML algorithms for sales forecasting. [ABSTRACT FROM AUTHOR]

With a focus on seafood industries, this study provides a framework for economic contribution assessments, outlines Virginia's seafood supply chain components, and evaluates the direct, indirect, and induced economic impacts of Virginia's seafood industry in 2019. Utilizing an analysis-by-parts method in IMPLAN, primary expenditure data from watermen, aquaculture farmers, processors, and distributors were collected through surveys. The efficacy of obtaining primary data through stakeholder surveys heavily relies on the investigator's interpersonal skills to establish trust and elucidate the study's benefits, particularly its potential to inform policy decisions. In 2019, the Virginia seafood industry's estimated total economic contributions amounted to USD 1.1 billion, supporting 7187 individuals. This impact encompasses 6050 direct jobs, 523 indirect jobs, and 614 induced jobs, primarily benefiting watermen and coastal communities. Furthermore, the industry's influence extends beyond its immediate economic sphere, supporting diverse sectors such as polystyrene foam manufacturing, boat building, sporting and athletic goods, and commercial and industrial machinery. Wages and salaries disbursed throughout the seafood supply chain ripple to Virginia's economy, benefiting nondepository credit intermediation, owner-occupied dwellings, and real estate sectors. Future research focusing on seafood sales in restaurants and retail outlets will complete the understanding of the seafood industry's broader economic impact on the state. [ABSTRACT FROM AUTHOR]

Artificial intelligence and the underlying machine learning (ML) methods are increasingly finding their way into our working world. One of these areas is sales planning, where machine learning is used to leverage a variety of different input parameters such as prices, promotions, or the weather, to forecast sales, and therefore directly affects the production of products and goods. To satisfy the goal of environmental sustainability as well as address short shelf life, the food industry represents an interesting application field for the use of ML for optimizing sales planning. Within this paper, we will examine the design, and especially the application, of ML methods in the food industry and show the current challenges that exist in the use of such concepts and technologies from the end-user's point of view. Our study of a smaller bakery company shows that there are enormous challenges in setting up the appropriate infrastructure and processes for the implementation of ML, that the output quality of ML processes does not always match the perceived result quality, and that trust in the functioning of the algorithms is the most important criterion for using ML processes in practice. [ABSTRACT FROM AUTHOR]

Forecast accuracy is a crucial topic for industrial companies, and its impacts are particularly important for the finance and production departments. The company can incur high costs if forecasts are inaccurate, for example, due to stock-outs or excess inventory. Therefore, this study aimed to optimize accessories forecasting for a medium-sized Swiss enterprise. To do so, different forecasting techniques were tested, and statistical methods and machine learning (ML) algorithms were compared. The results were adjusted according to key account managers' (KAM) expertise. This paper presents a comparison between exponential smoothing, seasonal autoregressive integrated moving average (SARIMA), SARIMAX (SARIMA with exogenous variables) and ML algorithms, such as knearest neighbors (k-NN), least absolute shrinkage and selection operator (LASSO) regression, linear regression, and even random forest (RF). To compare these different methods, two measures of statistical dispersion are computed: mean absolute error (MAE) and root mean squared error (RMSE). The results are standardized to enable a better comparison. For our dataset, SARIMAX (with the KAMs' expertise as an exogenous variable) gives better results than all the ML algorithms tested. [ABSTRACT FROM AUTHOR]

Software programmers may get gradually precise at expecting consequences without being clearly coded using machine learning techniques. Machine learning is based on the idea that models and algorithms may collect input data then utilize statistical investigation to determine an output, while updating results as information become obtainable, as underlying principle. For example, models may be adapted and trained to meet management expectations so that correct measures are followed to reach a certain goal. Wall Mart, a one-stop shopping mall, has been used in this system to estimate sales of various products and to study impact that various variables have on sales of products. Predictive models may be built using different features of a Wall Mart dataset and methods used to construct them, and these findings can be used to make better business choices. This Predictive Algorithm is used in many fields over the market world for their profitability. Recently, Lot of companies are going to used this Machine Learning for better AI and new technologies in market. This report Includes combination of machine learning algorithm and Features Engineering to predict Walmart sales. The research topic of this paper primarily solves the problems of Walmart sales forecasting that is provided by the Kaggle competition. [ABSTRACT FROM AUTHOR]

In the ever-evolving world of e-commerce, understanding customer behavior and predicting their spending patterns is crucial for businesses to thrive. This work presents an innovative application designed to predict customer spending on an e-commerce website. By leveraging advanced machine learning techniques and utilizing comprehensive customer data, the application offers valuable insights that can be used to optimize sales strategies and enhance customer experiences. The application employs a robust predictive model trained on historical customer data, including purchase history, browsing patterns, demographic information, and transactional details. the application incorporates real-time data updates to ensure continuous improvement and adaptability to changing customer behaviors. the proposed application offers a powerful tool for e-commerce businesses to predict customer spending, optimize sales strategies, and deliver personalized experiences. By harnessing the power of machine learning and leveraging comprehensive customer data, businesses can stay competitive in the dynamic ecommerce landscape and foster long-term customer loyalty. [ABSTRACT FROM AUTHOR]

Global economic growth, marked by rising GDP and population, has spurred demand for essential goods including furniture. This study presents a comprehensive demand forecasting analysis for retail furniture sales in the U.S. for the next 36 months using Multiple Linear Regression (MLR) and Holt–Winters methods. Leveraging retail sales data from 2019 to 2023, alongside key influencing factors such as furniture imports, consumer sentiment, and housing starts, we developed two predictive models. The results indicated that retail furniture sales exhibited strong seasonality and a positive trend, with the lowest forecasted demand in April 2024 (USD 9118 million) and the highest in December 2026 (USD 13,577 million). The average annual demand for 2024, 2025, and 2026 is projected at USD 12,122.5 million, USD 12,522.67 million, and USD 12,922.17 million, respectively, based on MLR, while Holt–Winters results are slightly more conservative. The models were compared using the Mean Absolute Percentage Error (MAPE) metric, with the MLR model yielding a MAPE of 3.47% and the Holt–Winters model achieving a MAPE of 4.21%. The study's findings align with global market projections and highlight the growing demand trajectory in the U.S. furniture industry, providing valuable insights for strategic decision-making and operations management. [ABSTRACT FROM AUTHOR]

Objective: The objective of the article is to examine the catering challenges for hospitality workers versus ticket sales at the Melbourne International Comedy Festival (MICF) in terms of their entrepreneurial behaviour. Research Design & Methods: This qualitative conceptual paper is based on interviewing hospitality workers at the MICF. Semi-structured interviews were used to survey venue managers and temporary hospitality workers whilst working at the MICF. Findings: The findings showcase that although some service processes at international comedy festivals can improve, it is unlikely to change in any significant way due to the nature of how comedy festivals are operated and for the duration for the individual shows. It is not feasible to have too many full-time staff or event parttime staff when a temporary or casual work force can service ticket holders even though some people may have a negative experience. Therefore, the workers need to develop entrepreneurial skills in order to succeed in the competitive marketplace. Implications & Recommendations: Investigating the challenges hospitality workers experience at the MICF when ticket sales are continually sold up until the performance is the first attempt at qualitative research in this field of study bridging the gap in event management, festival, and hospitality literature. It highlights the use of temporary hospitality workers as the main labour force of international comedy festivals and showcases some of the challenges hospitality workers experience. It acknowledges the need to think outside the box and to be innovative with work decisions. Contribution & Value Added: This paper adds to the growing body of literature in challenges for the hospitality industry, temporary hospitality workers, international comedy events and last-minute ticket sales and offers practical implications to assist in future large-scale comedy and fringe festivals for the first time. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to apply and verify Fourier series analysis in combination with non-linear regression as a tool of forecasting and planning of inputs in the logistics process of a retail chain store. Design/methodology/approach: For many popular products, a significant effect of seasonality of sales is expected; therefore, the method of Fourier series was chosen as one of the main forecast calculation techniques. However, the use of this method directly for forecasting sales has a limitation in the form of a complete reconstruction of the shape of the curve from of the given monitored time. Thus, the forecast is based only on the significant harmonic components from the Fourier series analysis that will participate in forecast forming. In addition, to respect the trend of series, the results of Fourier series analysis are combined with the non-linear regression. Findings: The results showed that the number of significant harmonic components from the Fourier series analysis is suitable to reflect the future behaviour of the sale in standard market conditions. Forecasting of the sale and accurate purchase planning of goods has a positive effect on reducing the waste of unsold products after their shelf and on increasing of a customer satisfaction. Research limitations/implications: This study has an application in a certain period of time (relatively calm behaviour of the food market) and only for a certain region. Therefore, it is not possible to generalize these results as the behaviour of consumers, e.g. within the state. It will also be interesting to monitor and forecast sales of other food items. Practical implications: This provides a practical and relatively simple tool for implementing or improving the process of forecasting seasonally dependent products in the food industry. Originality/value: This study shows the possibility of forecast that is based on adding the significant harmonic components from the Fourier series analysis to form forecast with the non-linear regression. [ABSTRACT FROM AUTHOR]

The early phase of launching a new apparel product is critical for gaining insights of its performance and classifying it into different categories such as fast selling, average selling, and slow selling. We propose a new ranking-based method to identify the product popularity that predicts regional and national rankings of products based on sales data at an early stage of a sales season. Our method enables companies to efficiently identify popular products within a remarkably short span of two to four weeks. The early phase of launching a new apparel product is critical for gaining insights of its performance and classifying it into different categories such as fast selling, average selling, and slow selling. This information is crucial for optimizing product management strategies and making decisions regarding inventory planning, pricing, and marketing. Many apparel companies rely on rule-based methods conducted by experienced sales managers, which consume significant time and energy from managers and often result in delayed information and low prediction accuracy. We propose a new ranking-based method to identify the product popularity that predicts regional and national rankings of products based on sales data at an early stage of a sales season. Our method enables companies to efficiently identify popular products within a remarkably short span of two to four weeks. To validate its efficacy, we compare the model's predictions with actual orders from a fashion company in 2021, showcasing a notable 5.9% increase in sales volume when using our approach to guide order decisions. Funding: J. Wang's work is supported in part by the National Natural Science Foundation of China [Grants 71931009 and 72171212]. S. Wu's work is supported in part by the Key R&D Program of Zhejiang Bilateral Industry Joint R&D Plan Project [Grant 2023C04047]. Q. Jin's work is supported in part by the National Natural Science Foundation of China [Grants 72010107002, 71821002, and 72171212]. [ABSTRACT FROM AUTHOR]