May-June 2018

Frontline Systems, developer of the Solver in Microsoft Excel, has launched Solver.Academy, its online learning platform for predictive and prescriptive analytics. Frontline also announced that it has surpassed 500,000 users of its cloud-based advanced analytics tools, aimed at spreadsheet-literate business analysts who aren’t expert data scientists.

“We’ve helped hundreds of thousands of non-experts build and solve advanced analytics models,” says Daniel Fylstra, Frontline’s founder and president. “We’re closing the ‘skills gap’ that would otherwise limit deployment of analytics methods in business.”

Solver.Academy, an online learning platform and formerly available only to select customers for general use. Built on Open edX – the software that powers the edX.org MOOC (Massive Open Online Course) platform – Solver.Academy offers self-service courses in data mining and predictive analytics, Monte Carlo simulation and risk analysis, and mathematical optimization. Each course is divided into six “weekly sections,” but these can be taken at the learner’s own pace. Each section includes video lectures and a quiz, and each course also includes a mid-term and a final exam, where learners must build and solve real models to pass. Frontline offers certificates for course completion, but the greater value for many course-takers is immediate application to their own business problems.

AIMMS announces release of Collaborative Data Management

AIMMS recently announced the release of Collaborative Data Management (or CDM for short), a functionality that allows developers to turn any AIMMS end-user app into a multi-user App.

AIMMS allows modelers to create decision-support apps for their end-users. Being able to play with the input data of the model and observe the consequences on the actions suggested by the model, is essential for the end-users to gain confidence in the solution(s) presented. With CDM, it is now possible to collaborate with other users and review each other’s changes.

CDM implements version control on AIMMS model data, very similar to the functionality offered by modern version control systems such as git. It offers a version control repository for AIMMS data within a regular relational database, with all data being stored in a tree of branches (or revision sequences). CDM enables you to:

• check out the data snapshot in a particular revision;
• commit, pull, revert and select change sets;
• create and merge branches; and
• resolve merge conflicts.

CDM also offers the capability to automatically commit and pull changes. All of these functionalities combined allow AIMMS modelers to create versatile multi-user work flows for decision-support apps that are suitable for a range of use cases.

Four new products announced at FICO World 2018

At its FICO World 2018 conference in Miami Beach on April 18, analytics software firm FICO unveiled several solution upgrades that will help banks, lenders, fintechs and other institutions fight financial crime. These solutions bring unparalleled efficiency and machine learning capabilities to fraud, risk and compliance professionals.

FICO Falcon Platform, designed to adapt fraud defenses across all channels, with each transaction, will provide third-party model support that allows users to deploy analytic models created by their own data science teams. This Falcon Platform 6.5 release also includes new executive dashboards that make it easier for fraud teams to track detection performance across a variety of financial products while monitoring evolving fraud vectors and distribution trends.

Anti-Money Laundering (AML) Advanced Analytics leverages supervised and unsupervised machine learning to combat money laundering. These analytic models use explainable AI techniques to efficiently detect money laundering, reduce false positives and prioritize alerts that require further investigation. The models complement rules-based AML systems to increase efficiency, improve speed of detection, and reduce operational costs associated with false positives.

FICO Card Compromise Manager 2.0 leverages advanced analytics and data from the billions of payment cards protected by Falcon Platform customers worldwide to detect data breaches and points of card compromise. Available this summer in the cloud, Card Compromise Manager enables card issuers and processors to proactively monitor cards at risk of fraud and execute risk management strategies within the Falcon Platform to minimize fraud losses while protecting consumers from harm.

FICO Application Fraud Manager, which helps institutions detect and prevent fraudsters from opening accounts, includes new rule simulation capabilities that allow organizations to evaluate new rules and policies against “what if?” scenarios. With this functionality, fraud managers can test new business rules to see if, working with machine learning algorithms, they can detect a greater percentage of fraudulent applications without slowing the approval process for legitimate customers, or increasing the false-positive ratio.