Nasah

Machine Learning

Next Generation Analytics

Machine Learning that is cost-effective, practical and fast to implement.

Principa’s analytics team have spent a number of years investigating machine learning technologies that are practical, cost effective and comply with the modelling standards expected by business. The end result is a combination of technologies in both analytics and data management that brings this technology to life – a solution we call the “Machine Learning Platform” (MLP).

Briefly how it Works

On a high level, the solution is able to ingest data from multiple sources, wrangle data for modelling needs and store modelling outcomes in the data management platform. Execution of the data models rests with Stratus – Principa’s propriety execution solution that incorporates model management and audit features, all critical features in a business ready machine learning solution. With this functionality in place, models can be retrained quickly and cost effectively based on customer needs and the application use. Standard or customisable reports continually monitor modelling outcomes.

The solution can be deployed both on customer premise or on a virtual server in the cloud.

Our machine learning offering is highly customisable based on customer needs and may be deployed in part or as a complete end to end solution.

What We Offer

Quick Step ML Model Building

Principa has developed a flexible machine learning model building approach (we call these Quick Step models). In this approach we can develop multiple concurrent models on a set of data. On a recent model building exercise, we used six different modelling techniques with three or four different parameter settings resulting in twenty-two different scores. Each score is then assessed for its discriminatory strength and for over-fitting to determine the most suitable model for the specific business problem. Quick step models are trusted with over 70 billion of our scores calculated annually.

Machine Learning Platform (MLP)

Principa can assist you in deploying your machine learning models on our proprietary Machine Learning platform. The solution is deployable on premise or in the cloud. Our ML platform covers the ETL process through our data management solution. We use various technologies to achieve this which is largely dependent on whether it’s an on premise or cloud deployment.

Machine Learning Model Management

Once machine learning models are built, models need to be deployed and managed. This means monitoring the stability of the data and the performance of the models. For this you need an experienced team that understand the various models, the data and the metrics that might indicate redevelopment is required. If a ML environment is built correctly, data should be modelling ready and redevelopment can happen rapidly.
Principa’s data science team have extensive experience in managing machine learning environments and models.

Get in Touch