Taxi fare prediction

Keywords: Taxi fare

Background

Taxi fare prediction plays a crucial role in the transportation industry, enabling passengers to estimate their expenses accurately and enabling taxi companies to optimize pricing strategies. In this study, we employ an ANN to predict taxi fare surge, represented as a binary variable (one or zero), based on various input features. The input columns include trip duration, distance traveled, number of passengers, fare, tip, miscellaneous fees, and total fare. The input variables are standardized to ensure consistent scaling across features. The ANN model is designed with multiple layers, including an input layer, hidden layers with ReLU activation functions, and an output layer with a linear activation function. The linear activation function in the output layer is suitable for regression problems, providing continuous predictions. To improve the model's performance and prevent overfitting, dropouts and batch normalization techniques are applied. During the training process, the model optimizes its parameters using the Adam optimizer and minimizes the mean squared error (MSE) loss function. The MSE loss measures the discrepancy between predicted and actual surge values, allowing the model to learn and make accurate predictions. After training, the performance of the model is evaluated using the R2 score, which measures the proportion of variance in the target variable explained by the model. In this study, the ANN model achieves an impressive R2 score of 93 percent, indicating its high predictive accuracy.

Aim & Objectives

Aim
To Predict the Taxi Fare Using DL Techniques
Objective

Research Methodology

ANN Technique used

Software & Tools

Jupyter, Google Collab

— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —