Machine Learning and Predictive Analytics
Predictive analytics are mathematical tools that analyse current or historical facts to predict future unknown events. Z/Yen has helped clients use these tools for since our founding in 1994, often classifying this work by its purpose, "dynamic anomaly & pattern response". Using support vector machines, initially built in-house and now with R, organisations with large data sets, such as donor information systems can classify and predict likely behaviours and outcomes. We do this as a weekly service for some clients. In other cases, e.g. pulmonary cancer detection from MRI scans, we combined use of neural networks, nearest neighbour, and decision tree approaches as appropriate resulting in a system deployed in China since 2005. With other clients we have worked to:
- Improve customer and member income and retention,
- Reduce volumes of unsuccessful contacts,
- Predict the effectiveness of grant making,
- Reduce errors and manual input in transaction processing.
Over the nearly three decades Z/Yen has worked with predictive analytics, the software tools required have shrunk from complicated and expensive bespoke applications to still complicated, but low cost or free, Excel add ons. Z/Yen are excellently positioned to help you understand how and when you can use Predictive Analytics. Our experience includes work with our original predictive engine PropheZy, as well as our visualisation tool VizZy.
