Predicting periodical sales of products using a machine learning algorithm

Document Type : Research Paper


Department of Computer Applications PSG College of Technology Coimbatore, India


Today, online shopping has evolved as a prominent business and there are very few opportunities for vendors to improve their sales. A machine learning algorithm can be used to predict what should be sold in a particular month so that sales can be increased. Once the Prediction is done a dashboard will be created to display which products should have been offered to have high sales. Billing the sales and analyzing with help of an expert is done. But in this case, not all people have the resources to get help from the experts. Vendors rely on their experiences. People who have started businesses for a few years lack experience and need support. To Help the vendors in improving their business a prediction of sales is done for each month and a dashboard will display the items to be sold in a particular month for an offer. To do Prediction Machine Learning Algorithms Random Forest Algorithm is used. This Algorithm is the best algorithm to do prediction and it is based on decision trees. The Scope of this project is developing the random forest model for predicting the sales of the products in each month from the year January 2013 to October 2015.


[1] T.F. Cootes, M.C. Ionita, C. Lindner and P. Sauer, Robust and Accurate Shape Model Fitting Using Random
Forest Regression Voting, Lecture Notes in Computer Science, Springer, Berlin, Heidelberg, 2012.
[2] U. Gro¨omping, Variable importance assessment in regression: Linear regression versus random forest, Amer.
Statistic. 63 (2009) 308–319.
[3] J. Han, Y. Liu and X. Sun, A scalable random forest algorithm based on MapReduce, 2013 IEEE 4th Int. Conf.
Software Engin. Serv. Sci. Beijing (2013) 849–852.
[4] Q. He, T. Shang, F. Zhuang and Zh. Shi, Parallel extreme learning machine for regression based on MapReduce,
Neurocomput. 102 (2013) 52–58.
[5] V. Svetnik, A. Liaw, Ch. Tong, J. Christopher Culberson, R.P. Sheridan and B.P. Feuston, Random forest: A
classification and regression tools for compound classification and QSAR modeling, J. Chem. Inf. Comput. Sci.
43(6) (2003) 1947–1958.
[6] W. Zhao, H. Ma and Q. He, Parallel K-Means Clustering Based on MapReduce, Lecture Notes in Computer
Science, Springer, Berlin, Heidelberg, 2009.
Volume 12, Special Issue
December 2021
Pages 1611-1630
  • Receive Date: 04 August 2021
  • Revise Date: 09 November 2021
  • Accept Date: 21 November 2021