Following up from a previous blog post about integrating Drools with the Open Prediction Service, in this new post we want to share the current results from another exploration work: this time integrating Drools with research on Transparent Machine Learning by IBM. Introduction Transparency is a key requirement in many business sectors, from FSI (FinancialRead more →
Introduction to TrustyAI and Drools Explainability is a crucial aspect in modern AI and decision services work; recent laws entitle any person subject to automated decisions to explanations of the intuition behind said decisions. Moreover, people are more likely to trust the decisions of explained models compared to unexplained models (Kim et al., 2022). Furthermore,Read more →
In this blog post we’re going to explore an integration between the Drools DMN Engine and another open source project from IBM: "Open Prediction Service" (OPS). Introduction Integrating symbolic AIs (rule engines, KRR, etc) with Machine Learning predictive models is an effective strategy to achieve pragmatical, and often more eXplainable, AI solutions. We have alsoRead more →
This blogpost introduces the event-driven predictions addon and is the third of my series of event-driven with Kogito posts, after the event-driven decisions and event-driven rules addons. It is available since Kogito v1.12.0 and its behavior resembles what the previous two addons already do for decisions and rules. Key concepts The new addon enables theRead more →
SHAP is soon to be the newest addition to the TrustyAI explanation suite. To properly introduce it, let’s briefly explore what SHAP is, why it’s useful, and go over some tips about how to get the best performance out it. A Brief Overview Shapley Values The core idea of a SHAP explanation is that ofRead more →
Sometimes the result of an automated decision may be neither desired or that which was required. What if there was a tool to find a way to overturn those decisions, maybe changing some of the figures that were provided to the system, and achieve a different outcome? That’s what we’ve been working on lately withinRead more →
In a previous blog post we have discussed how to leverage LIME to get more insights about specific predictions generated by a black box decision service. In fact LIME is mostly used to find out which input features where most important for the generation of a particular output, according to that decision service. Such explanationsRead more →
When working with decision services, it’s often hard to understand the rationale behind the output for a given prediction. A noteworthy example is the one related to having a decision service for loan approval denying the loan request to a given user. The user would surely like to know the rationale behind such a denial.Read more →
Monitoring is a well known concept in Kogito: the support for decisions was available since Kogito 0.11 through the Prometheus monitoring add-on. Today we announce that, starting from Kogito 1.11.0, this addon is enhanced to enable monitoring of processes. Unlike decisions, however, the feature is currently limited to operational metrics. The domain metrics section isRead more →
In a previous post (Shopping recommendations in PMML) we built the main infrastructure for making personalized shopping recommendations depending on the customer shopping history. The companion project was meant to demonstrate a standalone implementation of the Trusty-PMML engine. In this post, we will show how to invoke the engine on a remote Kogito instance. KogitoRead more →
