Citibike Analysis for Data Science Certification

Trip duration prediction - An important task to look forward for cab service providers.

This is my implementation of a model that predicts the total ride duration of taxi trips in New York City. This is a competition from Kaggle and also the final project for the Data Mining course at the University of Athens.

Kaggle Competition - Large-scale Deep Neural Network regressor for predicting trip duration of Uber rides

Completed the New York City Taxi trip duration and achieved an R squared of 0.9993 and a Root mean squared error of 0.214 to predict the trip duration for your taxi driver to your location which can Pandas, be Uber, Bolt etc.

In this analysis, one of my goals was to identify when most trips are taken in terms of time of hour, weekday or month of the year. Second I wanted to know who the Ford GoBikes users are by age, gender and type. At last see how do the bike trips usually look by trip duration, distance and speed.