Manually extracting information out of text traditionally requires many cost-inefficient human hours. Documents can be messy, unstructured and written in dozens of languages, all of which add significant complexity and cost for the company. Even for a human these aspects pose significant problems in terms of consistency and scalability; for a machine, they are considerably more manageable. We performed text extraction for a multi-national pharmaceutical company, extracting drug information from

Many companies have to deal with the issue of customer fraud and lost money due to false claims and representations. Many of these companies however have large amounts of data on their customers due to the nature of their business. Using this data effectively can allow companies to quickly identify possible cases of fraud without devoting large resources to manually reviewing cases. For this national energy company, we performed anomaly detection on time-series energy data, identifying dozens of likely fraudulent customers.

Raw time-series data of energy consumption can be disaggregated. This type of analysis allows a single dataset to be split into the likely appliances that each household is using. Such an analysis allows numerous benefits to energy companies and individual households - including optimised savings and environmental benefits.


Real-time object detection can be used in numerous ways, from cyber-security to autonomous vehicles. In this project, SFL used webcam data to automatically detect and classify instances of aggression between individuals and also collisions between vehicles at road-crossings.

Automatic document classification is a highly useful Natural Language Processing (text-based) analysis. In this particular case, physical patent applications were digitised and the the probability of the outcome of a particular patent was predicted.

There has been a recent surge of interest in using machine learning in medicine. Such a combination will yield remote and automated medical diagnoses, thus allowing more effective allocation of resources and ultimately saving lives. For this startup, we Identified likely cases of sleep apnea using purely audio data taken from overnight recordings, through a mobile phone app.

Wage gaps between gender and ethnic groups receive a lot of media coverage and are a major issue in our society. Identifying and addressing them effectively and accurately shields companies from lawsuits and bad publicity, whilst promoting equality and fairness.

Market segmentation is a typical analysis that allows companies to better understand their customer base. By broadly dividing a company's customers into segments, a company can understand and market to particular varieties of customers. 

A huge number of high quality photographs are being taken in the smartphone era. For many companies there is value locked within these images but the vast number of such images makes them tedious to sort through. Identifying features and objects in these images automatically allows companies to gather information in new ways and while expending fewer resources.

The process of tire manufacturing is the product of years of continuous research and advanced feats of engineering. The tire must achieve a balance between safety, comfort, traction, durability and efficiency. There are hundreds of components that contribute to the tire’s performance and fuel efficiency. We used traditional algorithmic development to model tire compression under load.