Quick Commerce: Product Price Classification Using Machine Learning Algorithms

Quick Commerce (Q-Commerce) is a trend that has led to the revolution of online retail by stressing on ultra-fast delivery within 10-30 minutes. In the current fast-paced market, dynamic prediction of products pricing plays an important role in optimizing pricing strategy and maintaining competitiveness. This paper compares classification methods for predicting products price categories in Q-Commerce, which is based on machine learning. For this, a thorough study is conducted on the data preprocessing and feature engineering and evaluating the classifiers: K-Nearest Neighbors (KNN), Naïve Bayes, Decision Tree, Random Forest, and Support Vector Machine (SVM).