Comparison Study

Abstract

The key to success in today's business is controlling the retails supply chain. Predicting customer demand is very essential for supply chain management. The perfect prediction has an effective impact on earning a profit., storage., lost profit., sales amount and consumer attraction. This article will produce a new method-using machine learning that will help for accurate prediction. This method collects the previous data of a store and analyze those data. Gathering the important information process those data and get prepared for using in method. Applying related algorithms towards the process data. We know K-Nearest Neighbor, Support Vector Machine, Gaussian Nave Bayes, Random Forest, Decision Tree Classifier and regressions have recently used an algorithm for prediction. We collect real-life data from the market. This paper made with the combination of shop position, month and occasion on that month and other related data. Our country's geographical area has an impact on prediction, which we discuss in our research. Our model produces a tentative demand for a particular product. This estimation helps retails and their businesses. After making a data set and apply appropriate algorithms, we will find different results and accuracy of different used algorithms. Compare them with others, we find out Gaussian Nave Bayes has the best accuracy. This helps to estimate the accurate product demand for a shop.