Use machine learning tools designed to allow non-experts to use advanced methods as responsibly as possible.
Clients using our ML tools often mention that it can be difficult to know which models to use. We generally advise users to start with the simplest appropriate model as a baseline (this is the default option), then to try additional models for comparison.
ML Team Lead
The IGI User Group 2025 meeting, held in June at Hallsannery, was one of our best-attended events to date, welcoming 15 participants from 10 different companies.
Managing Director​ & Data Scientist
He will be talking about the challenges of applying our new machine learning tools to geochemical data, motivated by work with DNO ASA on producing a holistic understanding the oils and source rocks of the North Sea.
Managing Director​ & Data Scientist
Tools to help you explore, explain and predict.
Use a series of data pre-processing steps to ensure your data is ready for machine learning modelling. This includes extreme value and outlier removal, dimension reduction, scaling of data and the treatment of missing values.
Select from a range of clustering models to group your data, or regression and classification models to predict values for continuous and discrete variables.
Use a range of diagnostic plots to understand the performance of your models and select an appropriate model for your problem. Use computational methods to automatically explore a range of model structures.
Explore your models in detail to examine the impact of each input variable, and understand why certain groupings occur when clustering.
The machine learning tools are in continuous development. Check the latest news to find out the latest features. Our aim is to provide advanced tools that can be used safely without needing to be a machine learning expert. Building on our deep understanding of statistics and machine learning you won't need to ask an AI - we've built the tools to help you make good choices!
