Document Type
Dissertation
Disciplines
1.2 COMPUTER AND INFORMATION SCIENCE, Computer Sciences
Abstract
Accurate sales predictions are essential for businesses in the fast-moving consumer goods (FMCG) industry. However, their demand forecasts are often unreliable, leading to imprecisions that affect downstream decisions. This dissertation proposes using an artificial neural network to improve intermittent demand forecasting in the retail sector. The research investigates the validity of using unprocessed historical information, eluding hand-crafted features, to learn patterns in intermittent demand data. The experiment tests a selection of shallow neural network architectures that can expedite the time-to-market in comparison to conventional demand forecasting methods. The results demonstrate that organisations that still rely on manual and direct forecasting methods could improve their predicting accuracy and establish a high-performing baseline for future development. The solution also offers an end-to-end systematic forecasting landscape enabling a lift-and-shift and easy transition from design to deployment. A practical implementation should bring about stable and reliable forecasts, resulting in cost savings, improved customer service, and increased profitability. Lastly, the research findings contribute to the broader academic field of forecasting and ML with a seminal proposal that provides insights and opportunities for future research.
Recommended Citation
Allende, U, (2023). Application of Shallow Neural Networks to Retail Intermittent Demand Time Series. [Technological University Dublin].
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 International License.
Publication Details
A dissertation submitted in partial fulfilment of the requirements of Dublin Institute of Technology for the degree of M.Sc. in Computing (Data Science) 02/03/2023.