Mc Colgans

Training a Model to Predict Product Demand

McColgan’s manufacture chilled food products and supply large and small supermarkets across the UK and Ireland. They currently have over 800 customers and manufacture over 1400 products.

The Challenge

The products McColgan’s manufacture have a short shelf life of approximately 18 days and customers generally demand a 14-day shelf life; this makes it challenging to maintain a suitable inventory whilst minimising waste. They have a human centric approach to forecasting, which is time consuming and reliant on spreadsheets. In 2023 £500k of orders were unfulfilled due to production shortage. Simultaneously, £1000s worth of product are discarded each month due to overproduction.

The Solution

It was identified that McColgan’s would benefit from a data-driven prediction system to help them maintain a suitable inventory whist minimising production waste. McColgan’s provided the Hartree NI Hub with 3 years of historical customer order data, which was extracted from their database as a CSV file. To derive value from the existing data, the Hartree Centre NI Hub supported McColgan’s in exploring how data science could perform data processing, exploratory data analysis and machine learning modelling, for future trend prediction. The Hartree NI Hub and McColgan's worked collaboratively to develop a number of data visualisations and a predictive model to forecast product orders and the forecast was provided against nine food products.

william mc colgan
We would have spent years trying to develop a solution ourselves. Working with the Hartree NI hub allowed us to get on with the application of the model, rather than developing it ourselves from scratch.
William McColgan, Director

Benefits

The project demonstrated the power of Artificial Intelligence technologies within the manufacturing and food sector. McColgan’s are empowered to use these technologies to extract additional value from existing data within their business.McColgan’s will initially run the predictive model in tandem to their current forecasting activities and will spend time evaluating the model and will use it to guide future planning. The project has already identified trends and periods of shortfall. A next step is to expand the model across other products and once their AIP is in place across 10 years of data. The accuracy of the model will continue to improve as more data is acquired, and in time, and they expect the model will outperform their human forecasting methods.

Further Information

This work was completed as one of our data projects. Our projects are up to 12 weeks in duration. We will work alongside your business to scope your project, demonstrate proof of concept, and explore options to deploy it within your business. If you would like to learn more about the Hartree NI Hub and our Programme, please get in touch with us at: info@hartreeni.uk

Our Impact on UK Industry and Society

The Hartree National Centre for Digital Innovation enables businesses to acquire the skills, knowledge and technical capability required to adopt digital technologies like super computing, data analytics, artificial intelligence (AI) and quantum computing. The SME Engagement Hubs play a key role in offering targeted support for business challenges in their region, creating value and generating economical and societal impact for the UK.