Knowledge Transfer Partnership with Clipper Logistics
- Start date: 17 January 2019
- End date: 13 May 2022
- Funder: Innovate UK
- Principal investigator: Professor Chee Wong, Dr Richard Hodgett, Professor Barbara Summers and Dr Sajid Siraj
- External co-investigators: Mr Nitin Jain (KTP associate)
One of the main challenges in analysing Big Data is the difficulty in collecting quality, longitudinal data from multiple sources, including sources not accessible by our customers. Another challenge is the possibility that individuals’ “returns” behaviours will change from time to time, leading to difficulty in reliably identifying consistent factors affecting a cluster of returns behaviours.
To address these challenges, we will need to use advanced methodologies, e.g. multi-criteria decision-making, supervised machine learning (regression, classification), unsupervised machine learning (clustering techniques), prediction heuristics, rough-set theories, text mining etc, and develop customised tools for performing predictions routinely.
This KTP project aims to develop and deploy models, incorporating predictive analytics techniques, that will significantly improve the processing efficiency and reduce the costs involved in handling product returns arising from fast fashion e-commerce transactions.