Frontline Systems is shipping Analytic Solver® V2023, a new version of its advanced analytics toolset for Excel (Web, Windows, and Macintosh), that enables business analysts to easily build models using business rules, machine learning, mathematical optimization, and Monte Carlo simulation, and easily deploy those models in cloud-based applications.
Analytic Solver is not new – it’s a market-leading analytics tool upward compatible from the Solver in Excel, which Frontline originally developed for Microsoft. But now it’s the first and only tool with fully automated methods for risk analysis of previously trained and validated machine learning (ML) models.
As an “Excel Solver upgrade”, Analytic Solver can handle virtually any type or size of optimization problem, ranging from a few to millions of inter-related decisions in a single model. And for years, Analytic Solver has offered powerful features for risk analysis using Monte Carlo simulation, and powerful features for training, validating, and deploying predictive models using machine learning.
Now, Analytic Solver V2023 includes an innovative capability for risk analysis of machine learning models that leverages multiple capabilities of the software. Risk analysis changes the focus from how accurately a ML model will predict a single new case, to how it will perform in aggregate over thousands or millions of new cases, what the business consequences will be, and the (quantified) risk that this will be different than expected from the ML model’s training and validation.
“With a patent application now on file to preserve invention rights, Analytic Solver users are the first to benefit from these innovative methods”, said Daniel Fylstra, Frontline’s President and CEO. Frontline Systems is concurrently releasing new versions of RASON®, its cloud platform for analytics, and Solver SDK®, its toolkit for software developers, with support for the same innovative methods.
Also Read: Upcoming Marketplace Will Help Emerging Natural Brands Expand Their Reach
How and Why Machine Learning has Lacked Risk Analysis
For a decade, data science and machine learning (DSML) tools – including Analytic Solver – have offered facilities for ‘training’ a model on one set of data, ‘validating’ its performance on another set of data, and ‘testing’ it versus other ML models on a third set of data. But this is not risk analysis: based on known data, it doesn’t assess the risk that the ML model will perform differently on new data when put into production use. While it’s common to assess a ML model’s performance in use, and move to re-train the model if its performance is unexpectedly poor, by that time those risks have occurred, often with adverse financial consequences. Quantification of such risks “ahead of time” has been missing in practice.