Predictive Analytics is commonly defined as leveraging technology that learns from data analysis to predict the future behavior of people or processes to drive better decision making. To effectively deploy large scale operations such as marketing campaigns, financial risk and fraud detection strategies, or cross-sell / up-sell strategies that involve multiple product offerings and distribution channels, predictive analytics places a probability against the outcome. For example, putting everything known about a customer into a model can generate an output that will predict whether that customer is likely to buy a new product, cancel a subscription, or introduce financial risk to credit lending.

Datawatch Angoss Decision Trees provide an interactive and intuitive interface for building and exploring segments and discovering relationships between variables. Decision Trees make no assumptions about the data and allow data scientists and business analysts to explore unfamiliar datasets and identify potentially good predictors against what they are measuring for. With no coding required, users can:

Leverage a powerful set of statistical algorithms against a complicated modelling task without having to create complex code

Easily incorporate business knowledge and policies while building segments Fine tune parameters and attributes for extensive algorithm control if need be

Let the model automatically show the relationship between variables, or manually determine where the model should display a variable relationship

Quickly understand indicators of predictive behaviour

Product details:

Customers Testimonials

“The future of direct marketing is using predictive analytics to either reduce costs or mitigate risk ”
“The savings from the reduced number of mailings was over $250,000. One way to improve a campaign is to increase response, the other is to reduce costs ”
Adam Eveline, Director Financial, Planning and Analysis, President’s Choice Financial


“We considered Model Builder & Enterprise Miner but decided to go with Angoss. The interface design was very appealing…it was easy to understand, and when you are building a decision tree you can change your dependent variable any time. That is very helpful.”
Risk Strategy & Development Manager, TD Canada Trust


“We use it (Angoss) quite extensively for strategy segmentations that we use to drive our credit policies.  We also use it to build risk-scoring models to interact with SAS.  I’m very pleased with their strategy builder which provides the ability to use more than one objective function when developing decision trees.”
Head of Analytics Competency Center – Global Modeling Support @ Citi Group


“We’ve had SAS Enterprise Miner, which is okay for decision trees, but it is something we use a lot at our company and we wanted a better provider for this. The product was much easier to use than SAS… it comes to results a lot more quickly.
Due to the company infrastructure at Angoss, we tend to get updates and support a lot more quickly than we do with SAS. It’s nice to call somebody who knows exactly what’s going on with the product.”
AVP, Credit Risk Management & Profiling, MBNA