Machine learning for predictive planning optimisation

Client

A leading global medical device company.

Background

To optimise its operational processes, our client sought to implement an application that could accurately predict ideal dosage ranges for products prior to processing.

The solution required a machine learning model capable of forecasting outputs based on key parameters like product density and processing speed. Training on historical data would enable the application to learn optimal dosage ranges to maximise efficiency and minimise risk.

With advanced machine learning capabilities required, the client partnered with Audacia given its track record delivering customised AI solutions. The project also represented an opportunity to pilot ML.NET, assessing its suitability for additional applications.

Solution

Audacia worked closely with the client to develop a sterilisation dosage predictor using ML.NET. Key steps included:

• Defining the core scenario and prediction requirements
• Importing and preparing historical data for model training
• Training a linear regression model using the LGM algorithm
• Testing the model locally and evaluating performance
• Enabling retraining as new data becomes available

The customised web application leverages the trained regression model to forecast ideal dosage ranges based on product details and processing parameters. Results are provided to administrators to optimise scheduling and dosage decisions.

Built on .NET Core using ML.NET, the application was designed for easy integration with the client's existing tech stack. Azure Machine Learning offered added flexibility for training models at scale.

Results

The ML.NET-powered dosage predictor delivered:

• 97%+ accuracy in forecasting optimal dosage ranges
• Faster prototyping compared to traditional ML approaches
• Easy integration with existing .NET systems
• Flexible training options via local or cloud resources
• A pilot for assessing ML.NET on future projects

By leveraging machine learning, the client gained data-driven insights to enhance quality control and maximise productivity. The success of the project highlighted ML.NET's power to deliver custom machine learning solutions efficiently.