Scoring Concepts Resources
This series of articles explores the foundational concepts behind building a performant and high-quality Batch Scoring solution in Quantexa. Each article breaks down a key component of the scoring process — from network generation and scoreable models to alerting and network pruning — offering practical guidance and design considerations. How will the articles help your team and deployment? Whether you're new to Batch Scoring or refining an existing implementation, this content provides a clear, structured approach to best-practice design. By understanding and applying these concepts, teams can ensure their scoring solutions are efficient, scalable, and investigator-friendly — ultimately driving better outcomes from their Quantexa deployments. Make sure you're signed in to the Community to access the articles. Articles in the series: Scoring Concepts: Run Date Scoring Concepts: In-Scope Customers Scoring Concepts: Scoring Levels and Scorecards Scoring Concepts: Scenarios & Risk Factors Scoring Concepts: Alerting and Re-alerting Scoring Concepts: Write-Once Steps Scoring DAG Design in Assess
Scoring Concepts: Scenarios & Risk Factors
This guide explains how to differentiate between Scenarios and Risk Factors. At Quantexa, we aim to give our clients meaningful Alerts. We focus on those that pose the highest risk to investigators. This article targets Business Analysts, Business End Users, and Subject Matter Experts (SMEs). It focuses on individuals engaged in risk assessment, decision-making, or developing Scores. When readers grasp these distinctions, they can design Scores and Scorecards better. This helps us show only the most relevant risk profiles to investigators. Read the full article for: Definition of Scenarios and Risk Factors Best Practices for Setting Scenarios vs Risk Factors How Scenarios and Risk Factors affect Alerting and Re-Alerting Using Detection Packs 4. Scoring Concepts: Scenarios & Risk Factors - Quantexa Community This article explains how to differentiate between Scenarios and Risk Factors. At Quantexa, we aim to give our clients meaningful Alerts. We focus on those that pose the highest risk to investigators. This article targets Business Analysts, Business End Users, and Subject Matter Experts (SMEs). It focuses on individuals…
Scorecard Tuning📋
Scoring is a key part of the Quantexa Platform, and to maximise effectiveness needs to be tuned in an ongoing iterative process. There are various elements in the scoring process that can be tuned, and this article serves as a guide as to methods that can be employed to do so. Read the full article (login required): 1. Scorecard Tuning - Quantexa Community Introduction Scoring is a key part of the Quantexa Platform, and to maximise effectiveness, needs to be tuned in an ongoing iterative process. There are various elements in the scoring process that can be tuned, and this article will serve as a guide as to methods that can be employed to do so. What can be Tuned? There are…
FinCrime Detection Pack 0.4 is now available
We are excited to announce version 0.4 of our FinCrime Detection Pack is now available in Early Access. This release introduces new features that will increase flexibility, improve score coverage and optimise score configuration to better capture desired behaviours, characteristics and events. This builds on the functionality released in version 0.3 of the FinCrime Detection Pack. Feature Highlights: You can now apply score logic on a targeted subset of transactions to help you uncover more specific underlying patterns that might otherwise be overlooked. You can now configure transaction score parameters based on the segment a score subject belongs to. This allows you to account for differences and ensure that you are capturing the behaviours and events you’re interested in. You are now enabled to select from a range of appropriate Event Windows to ensure that a score is targeting the desired behaviour or event. Target new risks with additional Score Types You can read more about the release in Detection Pack 0.4 Release (login required) For full details of the release, including compatible Quantexa Platform versions and minor enhancements, please see the Quantexa Documentation site. Release notes Migration guide
📢 New Education Program Launch 🚀 | Quantexa Technical Foundations Release 2
Education Services is delighted to announce Release 2 of our core technical eLearning Program Quantexa Technical Foundations. The Program is an entry point for users planning to work with our Platform in a technical capacity. This group includes future Quantexa Data Engineers, Scoring Engineers, Platform Architects, Business Analysts, and Project Managers. However, it is also an excellent resource for anyone looking to gain a deeper understanding of the Platform’s capabilities and key technical concepts. What’s new? Release 2 has been redesigned to offer a more efficient learning experience, featuring: A revised scope to reduce completion times, New interactive content and quizzes, Enhanced accessibility features, and Update to Demo version: 2.5.2. Program components: Introduction to Quantexa Decision Intelligence Platform Quantexa Foundations: Core Concepts Quantexa Foundations: Search Quantexa Foundations: Investigations Quantexa Foundations: ETL & Data Fusion Quantexa Foundations: Scoring with Assess What does the Release mean for Quantexa’s Customers and Partners? The updated content and format will enable our Customers and Partners to complete the Program more quickly and with less effort (within 3-4 days), allowing them to swiftly progress to more advanced programs and Academies. The Program has been redesigned to be more engaging and interactive, enhancing learning outcomes. Adding new accessibility features and rewriting the content will make the experience more inclusive for international audiences. When will the Program be available? Release 2 will be available as of June 25 for all new learners enrolled directly into the Quantexa Technical Foundations Program. The Program will be integrated (over the course of July) into all technical programs. Migration of eligible users from Release 1 to Release 2 is planned for July, with the aim of streamlining their learning experience. For further details on the range of programs our Quantexa Academy offers, read the following Community article: Introduction to the Quantexa Academy.
Detection Packs 0.2
What are Detection Packs? Detection Packs are a Scoring solution that enables projects to progress more quickly from resolved Entities and generated egocentric Networks to Alerts ready for investigation. Why are Detection Packs important? Using Detection Packs avoids the time and cost associated with writing the same Scores and Pipelines multiple times on different projects. This out-of-the-box Scoring solution provides a set of baseline Scores, so individual projects can focus on developing the complex Scores that match their specific needs. You can read more about the benefits of Detection Packs in 's article (log in required): For full details of the release, including compatible Quantexa Platform versions and minor enhancements, please see the Quantexa Documentation site (log in required).October Community Digest 🎃
Welcome to this spooktacular edition of our Community Digest, where we gather the most thrilling posts from our members just in time for Halloween 👻 Public content: 💬 Tips & Tricks for Managing Large and Complex Networks - Discussion 📅 Join our Monthly Community Connect on November 10th - Event 📣 Quantexa's Chris Bagnall wins ACAMS Today Article of the Year 2023 - Announcement 📚 Understanding Human Trafficking - Blog 💬 Elasticsearch and Why We Use It - Discussion 📚 Automatic Data Cleaning Through Data Normalisation and Statistics - Blog 📅 Unlocking the Power of pKYC: Smarter KYC Processes EMEA and APAC webinars 🏆Community Competition - Refer 5 Colleagues to Win! 📚 Elasticsearch Considerations for Quantexa - Blog 💬 Perspective: Addressing SEC-Identified AML Program Deficiencies at Broker-Dealers - KYC Group Discussion 📚 Using Data Fusion for the first time - Blog Members content (log in required): 💡Make dropdowns in Explorer charts searchable and sort options alphabetically in multiple languages - Idea ✔️Load Elastic not connecting - Academy Q&A 💡Auditing search viewer click event for audit monitoring - Idea ✔️When aggregating entity scores, only one appears in the customer scorecard - Q&A 💡Running out of screen real estate in the Investigation view - Idea Community quick links: 💡 Submit and vote for Ideas in our Ideas Portal 🗣️ Join one of our Specialist User Groups: FinCrime, Insurance, Data Management & KYC 📚️ Browse blogs, articles and guides in our Community Library New to the Community? Sign up for a Community Tour 😊Scoring Concepts: Alerting and Re-alerting 📖
Alerting is the name for the process that comes after Scorecard creation and before Task loading into a Quantexa Deployment. Alerting decides which Subjects in the Scorecard output should alert to the end-users. Re-Alerting is an Alerting process that occurs after the first Alerting cycle, when new Scorecard data becomes available. Re-alerting logic compares a Subject's Scorecard output with all previous Scorecard outputs. The aim of this process is to ensure that there is new material risk that an Investigator would like to review. It is strongly encouraged that all deployments with Batch Scoring implement Alerting. Read about the Alerting Framework, Alerting Threshold, and Score Types in Scoring Concepts: Alerting and Re-alerting. Read the full article (login required): 4. Scoring Concepts: Alerting and Re-alerting - Quantexa Community This article builds upon the concepts introduced in Scoring Concepts: Scoring Levels and Scorecards. Alerting is the name for the process that comes after Scorecard creation and before Task loading into a Quantexa Deployment. Alerting decides which Subjects in the Scorecard output should alert to the end-users. Re-Alerting…
Welcome to Quantexa 2.5 | 2.5.0 Release Announcement
We are pleased to announce Quantexa 2.5! Read below for a few exciting highlights. Stream Updates to the Entity Store The Entity Store can now be updated with a streamed ingest of new Documents, and creates a change log describing how the Entity population has changed. In combination with the ability to query the full population of resolved Entities, this update enables near real-time access to the most up-to-date view of your data. Why is this important? Users and downstream systems can now get the latest view of an Entity resolved by Quantexa, enabling business processes that need to access or act upon that update in near real-time - in a Master Data Management solution (MDM), for example - to do so. Deploy and Change Custom Scoring Pipelines through Configuration The addition of Scoring Extension Mode to the Assess Template Generation functionality helps simplify the process of setting up Scoring on a project. With the new Extension Mode, it is now possible to change and add new nodes to a custom Scoring model using configuration files. Why is this important? This significantly reduces the technical skills required for setting up the Scoring pipeline and makes the generation of a custom Scoring pipeline more flexible. Flexible Scorecards: Identify and Aggregate Insights Across Multiple Typologies Assess capabilities and helper functions have been added to support multiple Scorecards on the same level within one Scoring pipeline. Scores can contribute to one or more Scorecards and flexible alerting logic can be set up to include the outcome of multiple Scorecards. Why is this important? This enables the flagging of different types of risks or insights at the same level - for different typologies or different products, for example - and helps an investigator or analyst understand and act upon the full context of the data available. Tune Scorecards with QPython QPython utilities can now interact with Assess configuration files and Scoring pipelines, which simplifies the process of tuning a Scoring model, providing an easy way to conduct a what-if analysis. The interface, using pre-written Python Notebooks, calculates a set of the most common and useful metrics for tuning. The use of Jupyter Notebooks allows the export of the reports for inclusion in the wider model governance process. Why is this important? Scorecard tuning is one of the most important parts of model development, as the model must output the most relevant (e.g., risky or interesting) information for a specific use case. These utilities make the process of Scorecard tuning much more accessible, simple, and quick. It also makes sure that the model addresses the business need and risk appetite of the deployment. Other highlights Speed up and simplify deployment of Explorer with no-code configuration; Merge and split Entities, and override Entity Attributes through the Entity Management Panel (e.g., for Master Data Management solutions); Integrate with Kafka streaming typologies more easily. Share your thoughts on this release in our poll: Which feature of Quantexa 2.5 are you most excited for? To receive updates on every release, be sure to follow the Release Announcements topic: Want to learn more? Check out the Release Notes on the Quantexa Documentation site. If you are unable to access the Documentation site, please get in touch with your Quantexa point of contact or the Community team at community@quantexa.com.Individual Score Tuning Guidance
Tuning happens at different levels of granularity and in the Quantexa scoring model the lowest level of granularity is the individual Score. One or more Scores contribute to a Scorecard and the combined contributions give a total Scorecard value for alerting. The objective of tuning a Score is to show that it identifies intended behavior suitably with the configurations given by business. The recommended approach in Quantexa is above the line (ATL) and below the line (BTL) validation. Guidance for the first stage of tuning which is the individual Score level along with detailed steps of a synthetic worked example are covered in Individual Score Tuning Guidance (login required). Individual Score Tuning Guidance - Quantexa Community Tuning happens at different levels of granularity and in the Quantexa scoring model the lowest level of granularity is the individual Score. One or more Scores contribute to a Scorecard and the combined contributions give a total Scorecard value for alerting. The following guidance will be for the first stage of tuning…
