Food Delivery Time Prediction in Indian Cities Using Machine Learning Models
It addresses operational efficiency and customer satisfaction for food delivery services in densely populated Indian cities, but is incremental as it applies existing machine learning models to a specific domain with enhanced features.
This research tackled the problem of predicting food delivery times in Indian cities by integrating real-time contextual factors like traffic and weather, and found that the LightGBM model achieved an R2 score of 0.76 and MSE of 20.59, outperforming baseline methods.
Accurate prediction of food delivery times significantly impacts customer satisfaction, operational efficiency, and profitability in food delivery services. However, existing studies primarily utilize static historical data and often overlook dynamic, real-time contextual factors crucial for precise prediction, particularly in densely populated Indian cities. This research addresses these gaps by integrating real-time contextual variables such as traffic density, weather conditions, local events, and geospatial data (restaurant and delivery location coordinates) into predictive models. We systematically compare various machine learning algorithms, including Linear Regression, Decision Trees, Bagging, Random Forest, XGBoost, and LightGBM, on a comprehensive food delivery dataset specific to Indian urban contexts. Rigorous data preprocessing and feature selection significantly enhanced model performance. Experimental results demonstrate that the LightGBM model achieves superior predictive accuracy, with an R2 score of 0.76 and Mean Squared Error (MSE) of 20.59, outperforming traditional baseline approaches. Our study thus provides actionable insights for improving logistics strategies in complex urban environments. The complete methodology and code are publicly available for reproducibility and further research.