A Review On: Retailer Pricing Analysis using Machine Learning

Abstract

In this research, investigates deeply on price competition behavior between mobile commerce retailers (MCR) and traditional off-line retailers (TOR) in m-commerce era. On this basis, two related propositions are pointed out. First, it gets MCR’s and TOR’s perfect prices in competition, further analysis can find that in the competition between MCR and TOR when these two kinds of retailers coexist, two exterior factors and three inner factors decide the price difference. Second, as the penetrate rate of m-commerce increasing, perfect prices of two kinds of retailers will change, and the ratio of their change speed will be stable. The problem addresses price competition decisions to assist retailers in deciding just the right price in MCR and TOR while still subject to uncertainty. Efficient time series forecasting techniques, auction based market mechanism, Spot pricing, including the use of machine learning models, will help to reduce uncertainty and improve results by offering insight on future outcome-based decisions. One of the algorithms of machine learning that is used linear regression. It is easy to implement and is used for purposes such as predicting real estate prices, financialperformances and traffic. Cluster analysis is also used for the purpose of understanding the relationship between consumers and the products they mostly search for. This work proposes a hybrid model, exploring linear and nonlinear modelling. This information is used to aid the decision-maker in an optimization problem involving both the decision on the price in MCR and TOR and the best moment for the one-time per cycle retailer price replenishment in situations where the purchase price fluctuates in time. This work aims to present Regression Random Forests (RRFs) model to predict one- week-ahead and one-day-ahead spot prices. The prediction would assist retailer to plan in advance when to acquire spot instances, estimate execution costs, and also assist them in bid decision making to minimize execution costs and out-of-bid failure probability. In addition, we contribute to the literature by developing a detailed MCR and TOR channel choice model to drive the MCR and TOR operational decisions.