Taxi Trajectory Prediction-Predict the destination of taxi trips

Taxi Trajectory Prediction-Predict the destination of taxi trips

Given a partial trajectory of a taxi, you will be asked to predict its final destination using the taxi trajectory dataset.


Each project comes with 2-5 hours of micro-videos explaining the solution.

Code & Dataset

Get access to 50+ solved projects with iPython notebooks and datasets.

Project Experience

Add project experience to your Linkedin/Github profiles.

What will you learn

Understanding the problem statement
Importing the train and test dataset
Initializing important libraries and understanding its functions
Performing basic EDA on the Dataset
Plotting scatter graph In R
Fitting the best polynomial line between a graph
Using the method of extrapolation for making predictions
Extracting and converting predictions to Dataframe made using a graph
Saving the predictions in the CSV format

Project Description

It is important to predict the final destination of a taxi to enhance the efficiency of electronic taxi dispatching systems. When there is high demand, often there could be a taxi whose current ride can end near or exactly at the requested pick up location from a new rider. Predicting the final destination of taxi will help the dispatcher know where the driver would be ending their current ride so they can identify which taxi should be assigned for the next pickup request.

In this data science project, you will predict the destination of a taxi given the variable-length sequence of GPS points which represent the beginnig of its trajectory and other information in the taxi trajectory dataset such as taxi id, client information, date and time. The training data has details of all the taxi rides from 2013-2014 in the city of Porto, Portugal.  The taxi trajectory dataset represent around 1.7 million rides run by 442 taxis.

Similar Projects

Machine Learning Project in R -Predict which customers will leave an insurance company in the next 12 months.

In this deep learning project, we will predict customer churn using Artificial Neural Networks and learn how to model an ANN in R with the keras deep learning package.

Machine Learning Project in R-Detect fraudulent click traffic for mobile app ads using R data science programming language.

Curriculum For This Mini Project

03h 40m