ETA prediction of food deliveries
The food delivery time prediction model is essential in the food delivery industry, where timely and accurate deliveries are critical for customer satisfaction and overall experience.
I cleaned the dataset to eliminate errors and inconsistencies, ensuring the reliability and accuracy of the predictions.
Next, feature engineering was used to derive valuable insights from the dataset. By considering factors such as the delivery person's age, ratings, location coordinates, and time-related variables, key elements that affect delivery time were identified.
We then built the predictive model using regression algorithms like linear regression, decision tree, random forest, and XGBoost. The model was trained on a subset of the dataset using cross-validation techniques to ensure robustness. Model's accuracy was evaluated with metrics such as mean squared error (MSE) and R-squared (R2) score.
This food delivery time prediction model enables businesses to optimize their operations and enhance the overall delivery experience for their customers.
Note:-
files MyMain.py and Food Delivery Prediction.ipynb contains OpenCage api key.