CST4070 Applied Data Analytics Tools.

CST4070 Applied Data Analytics - Tools, Practical Big Data Handling, Cloud Distribution - Middlesex University

The challenge

Santander Cycles (formerly Barclays Cycle Hire) is a public bicycle hire scheme in London. The scheme`s bicycles are popularly known as Boris Bikes, after then-Mayor of London, Boris Johnson. The operation of the scheme has been contracted by Transport for London (TfL). The recent success of the scheme has led to its expansion into many areas of London and its rapid growth has led to real challenges balancing bike sharing supply with bike sharing demand.

To provide a possible solution to this problem, bike sharing usage prediction is critical. To this purpose, the Transport for London (TfL), has released three dataset - named bike_journeys, bike_stations and London_census- whose structure is illustrated in the next section.

As part of the challenge, you need to define and implement a data science method able to predict the total number of bikes rented in each bike station with the temporal granularity of one hour time slot, so to help TfL to balance bike sharing supply with bike sharing demand.

Special attention must be paid to the interpretation of the final adopted model, to understand which factors are associated with an high/low demand of rented bikes in London, such as population composition from census data, weekends, peak hours, and so forth.