Hossain, Muhammad IqbalAhmed, TanjilRahman, SalmanRouth, NiloyNirob, Eftakhar Alam2019-10-142019-10-1420192019-08ID 14101053ID 15301021ID 15301015ID 15201036http://hdl.handle.net/10361/12781Cataloged from PDF version of thesis.Includes bibliographical references (pages 34-35).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science, 2019.For improving business, the organization needs to analyze the buying pattern of their customer to keep track of all products that are being sold the most so that they could keep the stocks of those products and remove those which sells the least. Analyz- ing cross-selling, up-selling of products is one of the major issues for identifying the buying frequency pattern. We have proposed a machine learning-based model to rec- ommend and predict through K-Nearest Neighbor (KNN), fuzzy KNN (fKNN) Single Value Decomposition (SVD) algorithm to compare the best outcome. Our proposed recommendation model can be used to get an idea of which products need to keep more on their shelves and which products not for the convenience of the customers. Moreover, our proposed predictive model will help to forecast future pro tability with which business developer will be better equipped to see the bigger picture. So, we are hopeful our model will help to serve the interest of all the stakeholders.35 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Cross-sellingUp-sellingKNNfKNNSVD,RecommendationForecastingMachine learningThesis