Decision Trees in the Selection of Electric Vehicles Based on Various Parameters

The production of electric vehicles is highly increasing in recent days to meet the demands of alternatives to fuel-based vehicles. The automobile industries are manufacturing new variants of electric vehicles which are both economical and environmentally friendly. As the number of electric vehicles is many in the market it is quite challenging for customers to make decisions on selecting electric vehicles and also the retailers of E-vehicles are confronted with the same challenges of decision making. This paper proposes a decision-making model for selecting E-vehicles by using the machine-learning technique of Decision Trees. The decision-making on selection is based on significant parameters. The data on different E-vehicles with respect to the core parameters are subjected to treatment with the supervised learning technique of Decision Trees in the R environment. In this case, the decision trees are used to classify the E-vehicles into the two categories of feasible and infeasible based on five decision parameters. On comparing the accuracy results of classification with other machine learning techniques, decision trees are found to be more optimal.