Search

Firmaların varlıklarını sürdürebilmeleri için, belli karlılık hedeflerini tutturmaları gerekmektedir. Firmalarda karlılık hedeflerine doğrudan etki eden faaliyetlerden biri de satın alma faaliyetleridir. Değişen dünya koşullarında satın alma süreçlerinin kritik malzeme grupları için çevik ve stratejik olması gerekmektedir. Bu çalışmada, çelik malzeme ürün grubunda fiyat tahminleme çalışması için veri madenciliği ve makine öğrenmesi yöntemleri ortaya konmuştur. Veri setinde bulunan gürültülü veriler tespit edilerek veri madenciliği teknikleri ile temizlenmiştir. Temizlenen veri seti makine öğrenmesi tekniklerinden hiyerarşik kümeleme ve k-ortalamalar yöntemleri kullanılarak ideal küme sayıları tespit edilmiştir. Bu analizde bulunan ideal küme sayısının doğrulaması farklı performans ölçütlerine göre doğrulanmıştır. Belirlenen kümede yer alan referanslar için hem yapay sinir ağları ile hem adaptif ağ yapısına dayalı bulanık çıkarım sistemleri (ANFIS) ile fiyat tahminlemesi yaparak hangi yöntemin diğerine göre daha üstün olduğu ortaya konmuştur. Bu çalışmada önerilen analizler ile satın alma süreçlerinde, çalışan kaynaklı hataların satın alma stratejileri geliştirme süreçlerindeki etkileri azaltılmış, satın alma çalışanlarının uzun zaman harcayarak yaptığı analizler, endüstri mühendisliğinin teknikleri içerisinde yer alan veri analizi ve makine öğrenmesi yöntemleri ile gerçekleştirilmiştir. For the sustainability of companies, it is necessary to meet certain profitability targets. Purchasing function is one of the crucial functions that directly affects the profitability targets of companies. It has become a necessity to act agile and strategically for critical material groups in changing world conditions of purchasing functions. In this study, data mining and machine learning methods has presented to forecast price of steel material product groups. The noisy data in the data set was revealed and cleaned with data mining techniques. The data set was analyzed by clustering analysis such as hierarchical clustering and k-means methods. Optimal number of clusters was determined and validated by different methods. For the references in the selected cluster, price forecasting models was presented by using artificial neural networks (ANN) and adaptive network based fuzzy inference systems (ANFIS) The proposed forecasting model aims to reduce the effects of purchasing employee related errors in strategy development process for purchasing decisions and the analyses made by purchasing experts by spending a long time were carried out with industrial engineering methods such as data mining and machine learning algorithms.

The use of information technologies not only in production processes, but also in pricing, can increase the value created by companies; however, the penetration of the technologies at the company level are still insufficiently analyzed. Paper aims to reveal IT-related prerequisites for the change towards advanced price estimation process of customized products. Based on the results of a quantitative survey of Baltic furniture manufacturing companies, the extent and main applications of technology penetration and their links to price estimation practices and company performance were identified. A model of key factors of IT adoption in furniture production was developed.

Agriculture plays a vital role in Indian economy. It contributes 18% of total India’s GDP. In India, most of the crops are solely dependent upon weather conditions. Hence, more yield of crops can be achieved by analyzing agro-climate data using machine learning techniques. Machine learning (ML) is a crucial perspective for acquiring real-world and operative solution for crop yield issue. From a given set of predictors, ML can predict a target/outcome by using Supervised Learning. To get the desired outputs need to generate a suitable function by set of some variables which will map the input variable to the aim output. Crop yield prediction incorporates forecasting the yield of the crop from past historical data which includes factors such as temperature, humidity, ph, rainfall, crop name. It gives us an idea for the finest predicted crop which will be cultivate in the field weather conditions. These predictions can be done by a machine learning algorithm called Random Forest. It will attain the crop prediction with best accurate value. The algorithm random forest is used to give the best crop yield model by considering least number of models. It is very useful to predict the yield of the crop in agriculture sector.

The article contains results of information systems analyses that are used for real estate estimation and are based on artificial intelligence. A correlation analysis of the characteristics of real estate objects has been carried out. Data processing, as well as comparative analysis of artificial intelligence algorithms with computation of accuracy, error and deviation were implemented. A number of experiments were realized to select the hyper parameters of the algorithm. The characteristics that have a positive effect on adequacy have been determined

The aim of this research was to compare consumer expectations of quality of tomatoes based on disclosed price and later estimate the unknown price of tomatoes based on its tasting. One hundred six participants tasted four types of tomatoes with disclosed prices and with unknow prices and fulfilled the questionnaire. We focused on analysing how recognition of prices affects customer behaviour and price estimation of additional products. Using descriptive statistics and machine learning techniques in WEKA software we got results. The findings of this study corroborate that the knowledge of current prices significantly affected participants’ perception of the quality of the tomatoes being tasted; affected 63,21% students’ maximum price limits that they are willing to pay for tomatoes and make 32,77% of students use known prices and its rounded values to evaluate prices of additional products.

The correct real estate property price estimation is significant not only in the real estate market but also in the banking sector for collateral loans and the insurance sector for property insurance. The paper focuses on both traditional and advanced methods for real estate property valuation. Attention is paid to the analysis of the accuracy of valuation models. From traditional methods, a regression model is used for residential property price estimation, which represents the hedonic approach. Modern advanced valuation methods are represented by the artificial neural network, which is one of the soft computing techniques. The results of both methods in residential property market price estimation are compared. The analysis is performed using data on residential properties sold on the real estate market in the city of Nitra in the Slovak Republic. To estimate the residential property prices, artificial neural networks trained with the Levenberg-Marquart learning algorithm, the Bayesian Regularization learning algorithm, and the Scaled Conjugate Gradient learning algorithm, and the regression pricing model are used. Among the constructed neural networks, the best results are achieved with networks trained with the Regularization learning algorithm with two hidden layers. Its performance is compared with the performance of the regression pricing model, and it can state that artificial neural networks can considerably improve prediction accuracy in the estimation of residential property market price. Doi: 10.28991/esj-2020-01250 Full Text: PDF

Real estate valuation uses 3 main approaches: income, cost and comparative. When applying the comparative method, correction coefficients based on similar real estate transactions are determined. In practice, the coefficients and similar real estate objects are usually determined by using qualitative approach based on the valuators’ experience. The paper provides an analytical method for the determination of correction coefficient, which limits subjectivity when using the comparative method for valuation. The provided analytical approach also integrates macroeconomic indicators in the calculation process. It also addresses issues when available historical real estate transaction data is limited. A machine learning approach was applied to determine the average price of real estate in the region, with the possibility of using this information to obtain correction coefficients where historical data was unavailable. Alternative research usually focuses on final price estimation of the selected real estate object; however, the valuation standard of Tegova released in 2018 does not allow for applying analytically based approaches for individual real estate object evaluation; these approaches can be used only as a supportive tool for valuators.

Objective: In this study we investigated the effect of seasonal thermal stress on milk production and milk compositions between Holstein and Jersey dairy cows under the temperateclimate in Korea.Methods: A total of 9 Holstein lactating dairy cows (2.0±0.11 parity) which had a daily milk yield of 29.77±0.45 kg, and days in milk of 111.2±10.29 were selected similarly at the beginning of the experiments in each season. Also, a total of 9 Jersey lactating dairy cows (1.7±0.12 parity) which had a daily milk yield of 20.01±0.43 kg, and days in milk of 114.0±9.74 were selected similarly at the beginning of the experiments.Results: Results showed that the average ambient temperature (°C) and temperature-humidity index (THI) were higher in summer, and were lower in winter (p

Immersive environments may restore relevant context during consumer sensory testing and hence, could yield better discrimination and reliability in acceptance tests compared to traditional methods. To date, no study has compared hedonic data from these settings to those obtained in an actual consumption environment. Presently, sixty-two red-wine consumers evaluated the same 4 wines in 3 environments—a traditional sensory booth, an immersive wine bar, and an actual wine bar. For each wine, subjects evaluated overall liking, future consumption habits, and price estimation. Interestingly, wine liking did not differ across the three environments (p = 0.076) nor was there a significant wine by environment interaction (p = 0.955). However, at the individual level, wine liking was less stable. For each subject, the magnitude of difference in liking scores for each wine was calculated between two environments. On average, the greatest difference in liking scores occurred between the traditional booths and the actual wine bar (1.7 ± 0.1) and was significantly greater than the difference in liking scores between the booths and immersive wine bar (1.4 ± 0.1, p = 0.008); the liking difference between the immersive and actual wine bar (1.6 ± 0.1) was intermediate. Consumption behavior was also differentially impacted by environment. Subjects were more willing to order the wines at a wine bar when evaluating in the actual environment compared to the traditional booths (p = 0.035). However, environment did not influence the subject’s willingness to purchase the wine to drink at home (p = 0.064). Generally, consumers were able to accurately differentiate price amongst the wines (p

Background: While more attention has been paid of late to utilization plans for big data in the healthcare sector worldwide, few scholars have addressed the value estimation of healthcare data. Accordingly, this study aims to propose an idea of a reasonable price estimation algorithm that can be applied to bidirectional exchange in healthcare data platforms.Methods: This study incorporates three methodologies for the data valuation, namely: cost-based, market-based, and impact-based approaches. The cost-based approach calculates the value of data based on the costs associated with data creation, management, and utilization. On the other hand, the market-based approach evaluates it by comparing the market price of a service similar to the data. Finally, the impact-based approach estimates the data value with an emphasis on improving future revenue generation and productivity as an effect of using the data.Results: The trading prices of healthcare data are determined by the sum of two prices—the fundamental price and the dynamic price. Here, the fundamental price can be further subdivided into the beginning value, complexity value, and network value. The beginning value is determined in proportion to the physical file size of the data, and the fundamental price is estimated by adding the complexity value and network value that can reflect the qualitative value (within 20% of the beginning value) of the data to the beginning value. First, the complexity value can increase if more personal information, more relevant information to the national health insurance system, and more recent and long-term information are included in the dimensions of identification, material, and time information inherent in healthcare data. Second, the network value reflects whether the data can be well linked with data from, not only the healthcare sector, but also from other fields and sectors. The higher the match rate between the attribute value keyword of the data and the healthcare search keyword of journals of excellence and portal services, the higher value is given. Finally, dynamic price reflects real-time preferences for the data and changes in data supply and demand as the actual exchange proceeds through healthcare data trading. To this end, dynamic value is determined within the upper and lower 5% band of the previous month's trading price based on the number of monthly views for the data, the number of downloads of summary data, and the number of actual purchases, and this is reflected in the next month's trading price.Conclusions: If the algorithm for estimating the trading price of healthcare data proposed in this study is applied to actual data trades, it would expand the transactions of healthcare data from both supply and demand sides. Also, in the processes of actual data exchange and the accumulation of actual data trades, continuing studies on the weighting parameters are needed to better reflect reality; such studies would enable the assignment of additional values or penalties.

The researchers of Harvard University found in a study that India has the potential to become one of the largest economy over next decade. As real estate is the second highest job creating sector, the first one is agriculture. The real estate sector will play a very important role in economy growth of India. A study of oxford economics tells that India has the potential to become world largest real estate market with around 11.5 million new houses per annum. Real estate sector has seen a boom in last two decades with increase in demand of new offices and residential buildings. Private investment reached around 1.47 billion US$ in 2019. In real estate sector in India, FDI reached around 25.04 billion US$. There are different factors which can affect the price of real estate like amenities, infrastructure, availability of land, affordability, and many more. Importance of the factors also depends upon the location and one should be careful at the time of selection of significant factors. It is very important to identify the important factors so that the approximation of the real estate price can be done. Here, regression techniques such as multiple linear regression, stepwise regression, and support vector regression are used for real estate price prediction.

In this study, we propose a novel approach for the valuation of swing options. Swing options are a kind of American options with multiple exercise rights traded in energy markets. Longstaff and Schwartz have suggested a regression-based Monte Carlo method known as the least-squares Monte Carlo (LSMC) method to value American options. In this work, first we introduce the LSMC method for the pricing of swing options. Then, to achieve a desired accuracy for the price estimation, we combine the idea of LSMC with multilevel Monte Carlo (MLMC) method. Finally, to illustrate the proper behavior of this combination, we conduct numerical results based on the Black–Scholes model. Numerical results illustrate the efficiency of the proposed approach.

In this concept paper, we explore some of the aspects of quality of continuous learning artificial intelligence systems as they interact with and influence their environment. We study an important problem of implicit feedback loops that occurs in recommendation systems, web bulletins and price estimation systems. We demonstrate how feedback loops intervene with user behavior on an exemplary housing prices prediction system. Based on a preliminary model, we highlight sufficient existence conditions when such feedback loops arise and discuss possible solution approaches.

Rice is fundamental need for Indonesia and most of its citizens are occupied as farmers. In Ploso, Jombang, there are several big grain mills. The enterprises must be clever to respond many obstacles on their business, that way will minimize their loss and increase profit. Loss factor in grain mills lay on the mistake when they made calculation of price estimation, one of them is grain damage. The calculation commonly used among farmer is the price of grain is divided by damage grain. This study was descriptive qualitative research to reveal factors that affected rice price based on damage grain calculation in mill enterprise located in Ploso, Jombang Regency. The study was conducted in four months from February 2019 to May 2019 which took place in UD Santoso located in Ploso, Jombang Region. The study has resulted that grain yield must be considered by rice millers as factors in affecting rice price based on damage grain calculation. To avoid it, there must be socialization for farmer and mill owner about factors that affect grain yield, rice price expectation based on grain price and solution about how to minimize grain loss.

In this study, a web model which provides price estimation in terms of Turkish Lira for Bitcoin, Ethereum and Ripple which are popular cryptocurrencies, is developed. Using the relevant model, the price estimation of these three crypto currencies between 21.09.2019 and 20.11.2019 is carried out on the web with dynamic data. Artificial intelligence methods such as adaptive neural fuzzy inference system, artificial neural networks, polynomial curve fitting and long short-term memory are used for price estimation. The aim of this study is to provide periodic forecasts to individuals or institutions interested in cryptocurrencies and to test the success of the exemplary model of the use of artificial intelligence in finance. When the forecastings that haven’t yet been realized at the relevant dates and the actual values are compared, the successful results show that the model is well established.

In this paper, we propose a novel procedure designed to apply comparable sales method to the automated price estimation of real estates, in particular, that of apartments. Apartments are the most popular residential housing type in Korea. The price of a single apartment is influenced by many factors, making it hard to estimate accurately. Moreover, as an apartment is purchased for living, with a sizable amount of money, it is mostly traded infrequently. Thus, its past transaction price may not be particularly helpful to the estimation after a certain period of time. For these reasons, the up-to-date price of an apartment is commonly estimated by certified appraisers, who typically rely on comparable sales method (CSM). CSM requires comparable properties to be identified and used as references in estimating the current price of the property in question. In this research, we develop a procedure to systematically apply this procedure to the automated estimation of apartment prices and assess its applicability using nine years&rsquo, real transaction data from the capital city and the most-populated province in South Korea and multiple scenarios designed to reflect the conditions of low and high fluctuations of housing prices. The results from extensive evaluations show that the proposed approach is superior to the traditional approach of relying on real estate professionals and also to the baseline machine learning approach.

Real estate is one of the essential and challenging fields in the market which reflects the economy, and it needs constant improvement. Business intelligence nowadays plays a significant role in enhancing the process of decision making and risk management in many different fields. One of the promising fields is the real estate investment market. This paper proposes a framework for an effective BI solution for analyzing the real estate market and estimating the price of the properties. The building of the BI solution, which passes through multiple phases is demonstrated.

Decision-making based on data analysis leads to knowing market trends and anticipating risks and opportunities. These allow farmers to improve their production plan as well as their chances to get an economic success. The aim of this work was to develop a methodology for price forecasting of fruits and vegetables using Queretaro state, MX as a case study. The daily prices of several fruits and vegetables were extracted, from January 2009 to February 2019, from the National System of Market Information. Then, these prices were used to compute the weekly average price of each product and their span commercialization in Q4 and over the median of historical data. Moreover, product characterization was performed to propose a methodology for future price forecasting of multiple agricultural products within the same mathematical model and it resulted in the identification of 18 products that fit the Seasonal Auto-Regressive Integrated Moving Average (SARIMA) model. Finally, future price estimation and validation was performed to explain the product price fluctuations between weeks and it was found that the relative error for most of products modeled was less than 10%, e.g., Hass avocado (7.01%) and Saladette tomato (8.09%). The results suggest the feasibility for the implementation of systems to provide information for better decisions by Mexican farmers.

In the world finance and technological development in finance, along with innovative financial instruments, have attracted investors. The most popular of these developments is undoubtedly Bitcoin, which is an output of the blockchain infrastructure .Bitcoin that is not connected to a central authority and contains cryptographic features, is one of the crypto moneys. The fact that Bitcoin does not depend on Central Authority and disclose the factors affecting its price by supply and demand have resulted in high volatility. In this study, firstly blockchain technology will be explained briefly and time-dependent price estimates for Bitcoin which is one of the important outputs of this technology, will be made. Artificial Neural Networks (YSA), which has become increasingly popular among estimation methods in recent years, has been used in the study and compared with ARIMA in traditional estimation methods. The sample of the study was created using daily closing prices between 02.02.2012 - 09.01.2018 dates. As a result of this study, both directions and values of estimated prices by artificial neural networks MPL (6-3-1) model between 10.01.2018 - 18.01.2018 have been more successful than ARIMA (1.1.6) model.