Search

Deep neural network (DNN) architectures such as recurrent neural networks and transformers display outstanding performance in modeling sequential unstructured data. However, little is known about their merit to model customer churn with time-varying data. The paper provides a comprehensive evaluation of the ability of recurrent neural networks and transformers for customer churn prediction (CCP) using time-varying behavioral features in the form of recency, frequency, and monetary value (RFM). RFM variables are the backbone of CCP and, more generally, customer behavior forecasting. We examine alternative strategies for integrating time-varying and non-variant customer features in one network architecture. In this scope, we also assess hybrid approaches that incorporate the outputs of DNNs in conventional CCP models. Using a comprehensive panel data set from a large financial services company, we find recurrent neural networks to outperform transformer architectures when focusing on time-varying RFM features. This finding is confirmed when time-invariant customer features are included, independent of the specific form of feature integration. Finally, we find no statistical evidence that hybrid approaches (based on regularized logistic regression and extreme gradient boosting) improve predictive performance—highlighting that DNNs and especially recurrent neural networks are suitable standalone classifiers for CCP using time-varying RFM measures. [ABSTRACT FROM AUTHOR]

Every contact centre engages in some form of Call Quality Monitoring in order to improve agent performance and customer satisfaction. Call centres have traditionally used a manual process to sort, select, and analyse a representative sample of interactions for evaluation purposes. Unfortunately, such a process is marked by subjectivity, which in turn results in a distorted picture of agent performance. To address the challenge of identifying and removing subjectivity, empirical research is required. In this paper, we introduce an evidence-based, machine learning-driven framework for the automatic detection of subjective calls. We analyse a corpus of seven hours of recorded calls from a real-estate call centre using Deep Neural Network (DNN) for a multi-classification problem. The study establishes the first baseline for subjectivity detection, with an accuracy of 75%, which is comparable to relevant speech studies in emotional recognition and performance classification. We conclude, among other things, that in order to achieve the best performance evaluation, subjective calls should be removed from the evaluation process or subjective scores deducted from the overall results. [ABSTRACT FROM AUTHOR]

Network reliability, named multistate stochastic cloud/edge-based network (MCEN) reliability afterwards, is defined as the probability that demands can be satisfied for an MCEN. It can be regarded as a performance indicator of the MCEN to measure the service capability. The concept of existing algorithms is to produce all of minimal system-state vectors for calculating MCEN reliability. However, such concept cannot response MCEN reliability in time when the MCEN scale becomes complicated in the Industry 4.0 environment. For providing MCEN reliability for decision making immediately, an architecture of a deep neural network (DNN) is developed to propose a prediction model for MCEN reliability such that MCEN capability with varied data can be learned promptly. To train the reliability prediction model, MCEN information is transformed to the suitable format, and the related information for DNN setting, including the determination of related functions, are defined with appropriate hyperparameters by using Bayesian Optimization. An illustrative case and a practical case of Amazon Web Service are provided to demonstrate the prediction model for MCEN reliability to show the availability and the efficiency. [ABSTRACT FROM AUTHOR]

Traditional stochastic optimization in financial operations research applications consist of a two-step process: (1) calibrate parameters of the assumed stochastic processes by minimizing a loss function, and (2) optimize a decision vector by reference to the investor's reward/risk measures. Yet this approach can encounter the error maximization problem. We combine the steps in a single unified feedforward network, called end-to-end. Two variants are examined: a model-free neural network, and a model-based network in which a risk budgeting model is embedded as an implicit layer in a deep neural network. We performed computational experiments with major ETF indices and found that the model-based approach leads to robust performance out-of-sample (2017–2021) when maximizing the Sharpe ratio as the training objective, achieving Sharpe ratio of 1.16 versus 0.83 for a pure risk budgeting model. Simulation studies show statistically significant difference between model-based and model-free approaches as well. We extend the end-to-end algorithm by filtering assets with low volatility and low returns, boosting the out-of-sample Sharpe ratio to 1.24. The end-to-end approach can be readily applied to a wide variety of financial and other optimization problems. [ABSTRACT FROM AUTHOR]

Forecasting energy demand has been a critical process in various decision support systems regarding consumption planning, distribution strategies, and energy policies. Traditionally, forecasting energy consumption or demand methods included trend analyses, regression, and auto-regression. With advancements in machine learning methods, algorithms such as support vector machines, artificial neural networks, and random forests became prevalent. In recent times, with an unprecedented improvement in computing capabilities, deep learning algorithms are increasingly used to forecast energy consumption/demand. In this contribution, a relatively novel approach is employed to use long-term memory. Weather data was used to forecast the energy consumption from three datasets, with an additional piece of information in the deep learning architecture. This additional information carries the causal relationships between the weather indicators and energy consumption. This architecture with the causal information is termed as entangled long short term memory. The results show that the entangled long short term memory outperforms the state-of-the-art deep learning architecture (bidirectional long short term memory). The theoretical and practical implications of these results are discussed in terms of decision-making and energy management systems. [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]

Hesitant attitudes have been a significant issue since the development of the first vaccines—the WHO sees them as one of the most critical global health threats. The increasing use of social media to spread questionable information about vaccination strongly impacts the population's decision to get vaccinated. Developing text classification methods that can identify hesitant messages on social media could be useful for health campaigns in their efforts to address negative influences from social media platforms and provide reliable information to support their strategies against hesitant-vaccination sentiments. This study aims to evaluate the performance of different machine learning models and deep learning methods in identifying vaccine-hesitant tweets that are being published during the COVID-19 pandemic. Our concluding remarks are that Long Short-Term Memory and Recurrent Neural Network models have outperformed traditional machine learning models on detecting vaccine-hesitant messages in social media, with an accuracy rate of 86% against 83%. [ABSTRACT FROM AUTHOR]

The global containerised trade heavily relies on liner shipping services, facilitating the worldwide movement of large cargo volumes along fixed routes and schedules. The profitability of shipping companies hinges on how efficiently they design their shipping network; a complex optimization problem known as the liner shipping network design problem (LSNDP). In recent years, approximate dynamic programming (ADP), also known as reinforcement learning, has emerged as a promising approach for large-scale optimisation. This paper introduces a novel Markov decision process for the LSNDP and investigates the potential of ADP. We show that ADP methods based on value iteration produce optimal solutions to small instances, but their scalability is hindered by high memory demands. An ADP method based on a deep neural network requires less memory and successfully obtains feasible solutions. The quality of solutions, however, declines for larger instances, possibly due to the discrete nature of high-dimensional state and action spaces. [ABSTRACT FROM AUTHOR]

In this study, we compare two methods for using neural networks to efficiently learn the price of derivatives. The first method, proposed by Funahashi (Quant Financ 21(4):575–592, 2021a), involves training the neural networks to learn the difference between the derivative price and its asymptotic expansion, rather than learning the derivative price directly. The target derivative price is then obtained by adding the approximate solution with the predicted value of neural networks. This method reduces the required amount of learning data, often by a factor of one hundred to one thousand, compared to the case where the derivative price is directly learned through neural networks. In the second method, established in this paper, the neural networks learn the difference between the derivative price written on the underlying asset price that follows the target complex stochastic process and the derivative price written on the underlying asset price that has a relatively simple stochastic process that has a closed-form solution for the target derivative prices. This method provides an alternative valuation method when no efficient approximate solution for the derivative value is observed and if one can arbitrarily determine the model parameters of the quasi-process that approximates the original process. We also propose a unified method to determine the model parameters of quasi-processes from underlying asset processes. These methods prove valuable in cases where general analytic solutions are absent, as seen in widely used financial models such as the stochastic volatility models. These cases involve time-consuming numerical calculations to generate learning data, highlighting the value of the two methods, which significantly compress calculation times. [ABSTRACT FROM AUTHOR]

This paper introduces AlphaVision, an innovative decision support model designed for stock price prediction by seamlessly integrating real-time news updates and Return on Investment (ROI) values, utilizing various machine learning and deep learning approaches. The research investigates the application of these techniques to enhance the effectiveness of stock trading and investment decisions by accurately anticipating stock prices and providing valuable insights to investors and businesses. The study begins by analyzing the complexities and challenges of stock market analysis, considering factors like political, macroeconomic, and legal issues that contribute to market volatility. To address these challenges, we proposed the methodology called AlphaVision, which incorporates various machine learning algorithms, including Decision Trees, Random Forest, Naïve Bayes, Boosting, K-Nearest Neighbors, and Support Vector Machine, alongside deep learning models such as Multi-layer Perceptron (MLP), Artificial Neural Networks, and Recurrent Neural Networks. The effectiveness of each model is evaluated based on their accuracy in predicting stock prices. Experimental results revealed that the MLP model achieved the highest accuracy of approximately 92%, outperforming other deep learning models. The Random Forest algorithm also demonstrated promising results with an accuracy of around 84.6%. These findings indicate the potential of machine learning and deep learning techniques in improving stock market analysis and prediction. The AlphaVision methodology presented in this research empowers investors and businesses with valuable tools to make informed investment decisions and navigate the complexities of the stock market. By accurately forecasting stock prices based on news updates and ROI values, the model contributes to better financial management and business sustainability. The integration of machine learning and deep learning approaches offers a promising solution for enhancing stock market analysis and prediction. Future research will focus on extracting more relevant financial features to further improve the model’s accuracy. By advancing decision support models for stock price prediction, researchers and practitioners can foster better investment strategies and foster economic growth. The proposed model holds potential to revolutionize stock trading and investment practices, enabling more informed and profitable decision-making in the financial sector. [ABSTRACT FROM AUTHOR]

One of the most important composite indicators (CIs) to assess the development of countries or regions is the human development index (HDI) which is used by the United Nations (UN) to rank countries. HDI has three dimensions including healthy life, population education, and standard of living. A total of four different sub-indicators are defined for these three dimensions. The UN evaluates and ranks all countries using a simple arithmetic or geometric average of the sub-indicators and then categorizes the countries into four different groups based on their HDI scores. To measure the HDI, the benefit-of-the-doubt (BOD) model is used by researchers instead of the geometric mean. The conventional BOD model has some main drawbacks. The first is not accounting for data uncertainty, and the second is evaluating countries using different weights for the same sub-indicators. Furthermore, BOD model is not capable of predicting countries' future HDI scores. To overcome these deficiencies, this paper proposes a common weight fuzzy BOD (CWFBOD) model to measure the HDI scores. First, to take into account the uncertainty, data are considered fuzzy numbers, and a fuzzy BOD model (FBOD) is introduced. Then, to find a set of common weights for the three dimensions of HDI, the proposed FBOD model is transformed into a multiple-objective CWFBOD model. To convert and solve the multiple objective CWFBOD model to a single objective model, a fuzzy theory approach is used. In addition, of predicting the future HDI scores of countries, an artificial neural network (ANN) is designed and trained, where the original data on sub-indicators health, education, and income are considered as the features, and the HDI scores generated by CWBOD are assumed as the target of ANN. Finally, this study applies the fuzzy C-Means clustering technique to cluster all countries into four different clusters based on the HDI scores generated by FBOD and CWFBOD models. To illustrate the ability of the proposed methodology, the HDI scores of 190 countries during the period of 2015–2021 have been estimated and predicted. The results show that the proposed integrated methodology can be effectively used to estimate and predict the HDI scores as well as to cluster countries. [ABSTRACT FROM AUTHOR]

Serial-batch scheduling problems are widespread in several industries (e.g., the metal processing industry or industrial 3D printing) and consist of two subproblems that must be solved simultaneously: the grouping of jobs into batches and the sequencing of the created batches. This problem's NP-hard nature prevents optimally solving large-scale problems; therefore, heuristic solution methods are a common choice to effectively tackle the problem. One of the best-performing heuristics in the literature is the ATCS–BATCS(β) heuristic which has three control parameters. To achieve a good solution quality, most appropriate parameters must be determined a priori or within a multi-start approach. As multi-start approaches performing (full) grid searches on the parameters lack efficiency, we propose a machine learning enhanced grid search. To that, Artificial Neural Networks are used to predict the performance of the heuristic given a specific problem instance and specific heuristic parameters. Based on these predictions, we perform a grid search on a smaller set of most promising heuristic parameters. The comparison to the ATCS–BATCS(β) heuristics shows that our approach reaches a very competitive mean solution quality that is only 2.5% lower and that it is computationally much more efficient: computation times can be reduced by 89.2% on average. [ABSTRACT FROM AUTHOR]