Customer Demand Forecasting via Support Vector Regression Analysis (original) (raw)
Related papers
Support Vector Machine Model for Demand Forecasting in an Automobile parts industry: A Case Study
isara solutions, 2019
Demand Forecasting is very crucial for any business organization. Many times people involved in business activities have to take decisions on which business prospects depends. The decision-making should be accurate and precise as company’s revenue depends on this. For this forecasting models are developed which aids in making decisions. The objective of this work is to study the basics of Support Vector Machine (SVM) and its application in supply chain management and develop an SVM model, which will predict the future demand with high accuracy as compared to the conventional forecasting methods. To demonstrate the effectiveness of the present study, demand forecasting issue was investigated in a piston manufacturing industry as a real world case study. In this proposed research, a SVM model is developed using radial basis kernel function and sigmoid function. Various factors that affect the product demand such as produced units, inventory, sales cost, and number of competitors have been taken into consideration in the development of model. A comparative analysis of SVM model and various traditional forecasting methods like exponential smoothing, moving average and autoregressive model has been done based on the results obtained from forecasting models.
International Journal of Information Technology & Decision Making, 2015
Sales forecasting is very bene¯cial to most businesses. A successful business needs accurate sales forecasting to understand the market and sales trends. This paper presents a novel sales forecasting model by integrating support vector regression (SVR) and bat algorithm (BA). Since the accuracy of SVR forecasting mainly depends on SVR parameters, we use BA for tuning these parameters because Bat is a newly introduced algorithm and has many parameters. In order to¯nd the best set of BA parameters Taguchi method was utilized. We validated our model on four known UCI datasets. Then we applied our model in printed circuit board (PCB) sales forecasting case study. We compared the accuracy of the proposed model with Genetic algorithm (GA)-SVR, particle swarm optimization (PSO)-SVR, and classic-SVR. The experimental results show that the proposed model outperforms the others. To ensure the robustness of our proposed model, sensitivity analysis was also done using our model to¯nd out the e®ects of dependent variables values on sales time series.
An application of support vector machines to sales forecasting under promotions
4OR, 2016
This paper deals with sales forecasting of a given commodity in a retail store of large distribution. For many years statistical methods such as ARIMA and Exponential Smoothing have been used to this aim. However the statistical methods could fail if high irregularity of sales are present, as happens for instance in case of promotions, because they are not well suited to model the nonlinear behaviors of the sales process. In recent years new methods based on machine learning are being employed for forecasting applications. A preliminary investigation indicates that methods based on the support vector machine (SVM) are more promising than other machine learning methods for the case considered. The paper assesses the application of SVM to sales forecasting under promotion impacts, compares SVM with other statistical methods, and tackles two real case studies.
Advances in Logistics, Operations, and Management Science
Reliable prediction of future demand is needed to better manage and optimize supply chains. However, a difficulty of forecasting demand arises due to the fact that heterogeneous factors may affect it. Analyzing such data by using classical time series forecasting methods will fail to capture such dependency of factors. This chapter addresses these problems by examining the use of feature selection in forecasting using support vector regression while eliminating the calendar effect using X13-ARIMA-SEATS. The approach is investigated in three different case studies.
Machine Learning Approach for Electrical Load Forecasting Using Support Vector Regression
Journal of Physics: Conference Series, 2019
The management of power system in Lhokseumawe, Indonesia is complex task for transmission operator and is heavily reliant on knowledge of future energy demand. The available data allows for the maturation of the electricity market and encourages analysis of data to improve the generation, usage and management of electrical power. Our research specially will be based upon the Lhoksuemawe, Aceh data set which gives the total load on electric grid measured in intervals for past several years. In particular, our methods will use machine learning approaches by using support vector machine regression to forecast the average total load on Lhokseumawe, Aceh grid one day head of time. The results will be practically beneficial as utilities can use the predicted values to generate an adequate amount of energy to avoid grid outages and electrical losses as well as construct dynamic pricing schemes based upon future load.
Day-Ahead Load Forecasting using Support Vector Regression Machines
International Journal of Advanced Computer Science and Applications
Accurate day-ahead load prediction plays a significant role to electric companies because decisions on power system generations depend on future behavior of loads. This paper presents a strategy for short-term load forecasting that utilizes support vector regression machines. Proper data preparation, model implementation and model validation methods were introduced in this study. The SVRM model being implemented is composed of specific features, parameters, data architecture and kernel to achieve accurate pattern discovery. The developed model was implemented into an electric load forecasting system using the java open source library called LibSVM. To confirm the effectiveness of the proposed model, the performance of the developed model is evaluated through the validation set of the study and compared to other published models. The created SVRM model produced the lowest Mean Average Percentage Error (MAPE) of 1.48% and was found to be a viable forecasting technique for a day-ahead electric load forecasting system.
Proceedings of the 39th Annual Hawaii International Conference on System Sciences (HICSS'06), 2006
This study develops a novel model, GA-SVR, for parameters optimization in support vector regression and implements this new model in a problem forecasting maximum electrical daily load. The realvalued genetic algorithm (RGA) was adapted to search the optimal parameters of support vector regression (SVR) to increase the accuracy of SVR. The proposed model was tested on a complicated electricity load forecasting competition announced on the EUNITE network. The results illustrated that the new GA-SVR model outperformed previous models. Specifically, the new GA-SVR model can successfully identify the optimal values of parameters of SVR with the lowest prediction error values, MAPE and maximum error, in electricity load forecasting.
Comparison of Time Series ARIMA Model and Support Vector Regression
International Journal of Hybrid Information Technology, 2020
As one of the most important and costly functions of any business, sales analytics has been the target of many studies for some time now. Knowing and tracking the sales of a business proves useful in all data-driven decisions made from inventory management to shelf layouts in a supermarket. However, forecasting sales rely heavily on data and algorithms strong enough to handle unseen data. Since sales data are in nature time series datasets one of such predictive methods is time series analytics. In this paper, the ARIMA modeling to the seasonality of the data is compared with a machine learning technique, support vector regression. These comparisons are carried out on three different and unrelated datasets and these algorithms' errors when predicting future sales are compared. The results obtained from our analysis show poor results in general due to datasets having large numbers of oscillation and outliers, but for comparison purposes these datasets and results are fine. We conclude that support vector regression produces better results in comparison with time series analytics on all datasets used in this paper.
Cash demand forecasting for ATM using neural networks and support vector regression algorithms
2 Vilnius University, Kaunas faculty, Muitinns g. 8, 44280 Kaunas 3 JSC Penkių kontinentų bankinns technologijos, Kalvarijų g. 143, Vilnius Abstract: In this paper two different methods are used to forecast the daily cash demand for automatic teller machines (ATM). The first method is based on flexible artificial neural network (ANN). The gener-alization properties of this ANN were improved using special adaptive regularization term. The second forecasting method employs the support vector regression (SPR) algorithm. Performed simulation studies and experimental tests showed tolerable forecasting capacities using the both proposed methods. Despite the today's overenthusiastic beliefs about the capabilities of SPR, our investigation showed however that for this application slightly better result can be achieved using forecasting method based on flexible ANN. At this stage the forecasting schema based on flexible ANN is in the implementing phase for intel-ligent cash management in...
THE AMERICAN JOURNAL OF ENGINEERING AND TECHNOLOGY, 2024
This study investigates the effectiveness of various machine learning models in predicting product demand based on customer satisfaction data. Four models—Linear Regression, Random Forest, Gradient Boosting, and Support Vector Machine (SVM)—were evaluated using performance metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R² score. The results indicate that Gradient Boosting achieved the highest accuracy, with an MAE of 2.56, MSE of 12.75, RMSE of 3.57, and R² score of 0.82, effectively capturing the complex, non-linear relationships inherent in customer satisfaction factors. Random Forest also demonstrated strong performance, while Linear Regression and SVM showed limitations in handling intricate datasets. These findings underscore the importance of utilizing advanced machine learning techniques for accurate demand forecasting, highlighting the critical role of customer satisfaction data in enhancing predictive capabilities. The insights gained from this research can guide organizations in optimizing inventory management and improving customer satisfaction in a rapidly evolving market.