Case Studies

Recent case studies


Anomaly Detection on Time Series

Anomaly detection is one of the most challenging tasks that we can find in different industries: a fraudolent payment in sales or credit card businesses, a mechanical piece breakdown in industrial production systems, or an excess of volatility in a financial time series. Using deep learning algorithms we are able to detect events that cannot be found in the systems' historical data and take appropriate corrective actions such as fraud warnings or predictive maintenance.


Document Mining using Deep Learning

Document mining is the process of extracting specific information from documents such as PDF files and using it to guide the decision-making process. By means of state-of-the-art deep learning algorithms, we are able to extract meaningful sentences from long documents so that analysts can focus their attention only on the most important parts of a document.


One-Click Credit

To overcome the necessity for Financial institutions to fulfil digital expectations, and be quick and proactive (and not just reactive) in extending credit to their active customer base, by anticipating the analytics, both in terms of risk and predicting customer needs, it was possible to assign eligible customers with pre-approved credit on multiple financial products.