Machine Learning (ML)

Seen as a game-changer for its ability to deliver personalization insight at a scale hitherto unseen, machine learning (ML) describes the use of algorithms to train a computer to look for patterns and infer truths from data instead of being explicitly programmed to act on the data.

What is a machine learning algorithm?

An algorithm is a set of rules or instructions used for performing calculation, data processing, automated reasoning, and other tasks. With reference to machine learning, algorithms look for patterns in data or infer truths from data, allowing the computer to then act on the patterns and the truths it infers, to make decisions that are more complex, or more subtle than would be possible to program explicitly.

How does Qubit use machine learning?

Machine learning powers a number of solutions provided by Qubit:

  • Opportunities

Uses clustering algorithms to group and identify interesting segments within your customer base.

  • Recommendations

Uses algorithms, from regression to matrix factorization, to suggest connections between products.

Where real-time category preferences and recommendation sources are inferred.

We also build on top of Google’s BigQuery machine learning to provide a number of predictive models about future visitor behavior such as propensity to purchase, next order value and individual preferences.