Charger Study: A Data Science Approach to Predict the Outcome of an EV Charger Getting Certified

Charger study aims to predict results of certification of Electric Vehicle (EV) DC fast chargers accurately by applying machine learning techniques to historical data. The historical data consists of rows where each row consists of several statistics for both the EV-maker charger and a 3rd party charger. The historical data is generated using web scraping libraries such as Selenium and Beautiful Soup. Based on the scraped data, data cleaning and feature engineering is done to generate several features of a charger like connectors used, power rating, voltage rating, current rating etc. Finally, the features are represented in a vector format and fed as inputs to different Machine Learning classifier algorithms like Multinomial Logistic Regression, SVM, Gradient Boosting Classifier and Decision Tree Classifier. After the classification, accuracy is measured by calculating percentage of correct predictions and percentage of correct no-certification for mistake correction predictions. Error analysis is performed using techniques like Region under Curve to tune hyper-parameters and to identify the features which are more prominent/useful in accurately predicting the results.