CIO Influence
Analytics CIO Influence News Cloud

Frontline Systems Releases Analytic Solver V2021.5 with Risk Analysis, Machine Learning, Model Deployment Enhancements

Frontline Systems Releases Analytic Solver V2021.5 with Risk Analysis, Machine Learning, Model Deployment Enhancements
Tool enables business analysts to create analytics-powered decision services, “point and click” without coding, using optimization, Monte Carlo simulation, data mining and machine learning, rules and decision tables; works in Excel for the Web, Windows and Macintosh and with Microsoft Teams.

Frontline Systems has released a major new 2021.5 version of Analytic Solver, its leading toolset for Excel for the Web, Windows and Macintosh, that makes risk analysis, Monte Carlo simulation, data mining and machine learning easier for business analysts, and further simplifies the task of deploying analytic models in cloud-based applications.

Analytic Solver works in Microsoft Excel to enable business analysts who aren’t data scientists to build and solve analytic models themselves. It is upward compatible from the Solver in Excel, which Frontline originally developed for Microsoft, and is able to solve virtually any type and size of optimization model.

Recommended ITech News: ITechnology Weekly Highlights : Top ITech News To Read

Decision Intelligence Results in Months, not Years

Analytic Solver works with RASON, Frontline’s Azure-hosted platform, to empower users to ‘publish’ and manage analytic models as RESTful decision services, easily usable in Teams, Power BI, Power Apps, Power Automate, or any application that can consume JSON or OData. The combination is a complete “decision intelligence suite” that supports business rules, forecasting, machine learning, optimization and simulation methods, from small models to large, multi-stage analytics workflows.

“With Analytic Solver, business analysts have unique risk analysis and machine learning capabilities – and they can ‘move beyond Excel’ to gain cloud-based data access, model management and governance, without losing the advantages of Excel”, said Daniel Fylstra, Frontline’s President and CEO.

Automate Data Mining with Find Best Model

Using Analytic Solver’s data mining and machine learning tools, users can “train” or fit data to a wide range of statistical and machine learning models: Classification and regression trees, neural networks, linear and logistic regression, discriminant analysis, naïve Bayes, k-nearest neighbors and more. But the task of choosing and comparing these models, and selecting parameters for each one was up to the user.

Recommended ITech News: RoboSense Became the First Solid-state LiDAR Provider Completed the SOP

With new “Find Best Model” options in V2021.5, this work is automated. Analytic Solver will test and evaluate multiple types of machine learning models and their parameters, validate and compare them according to user-chosen criteria, and deliver the model that best fits the data.

Better Simulation Models with Metalog Distributions and Fitting

Analytic Solver and RASON support over 60 “classical” probability distributions for Monte Carlo simulation. Since mid-2017, they’ve also supported the increasingly popular Metalog family of distributions, created by Dr. Tom Keelin: these tools can closely approximate virtually any classical continuous distribution, and often they can better fit historical data than classical distributions. Analytic Solver V2021.5 brings Metalog distributions to the fore, with a powerful new facility to automatically fit user data to the full range of possible (bounded and unbounded, multi-term) Metalog distributions. It’s never been easier to get an accurate probability distribution that fits a real-world phenomenon..

Share Machine Learning and Probability Models via RASON

In recent years, RASON has offered increasingly powerful facilities to deploy models to the cloud and share them with other users – culminating in Frontline Solvers V2020.5, which enabled deployment, sharing, versioning and management of Excel models as well as native RASON models, plus support for multi-stage decision flows, encompassing and going beyond traditional data science workflows.

Analytic Solver V2021.5 goes further: Users can now deploy and share data mining and machine learning models, trained in Analytic Solver or RASON, to the Azure cloud, and use them directly for classification and prediction (without needing auxiliary “code” in R or Python, RASON or Excel).

Users can also deploy and share probability models, following the open Probability Management 3.0 standard. With these tools, a large organization with multiple risk analysis and modeling projects can ensure they are using consistent assumptions about uncertain/risky variables, down to individual trials, in simulation or decision models – enabling results of different projects to be meaningfully compared.

Recommended ITech News: Bandwidth Ranked Top CPaaS Provider on Omdia’s Influential SIP Trunking Scorecard

Deployment Wizard for Teams, Power BI, Tableau and RASON

With Analytic Solver, business analysts can “deploy to the cloud,” and even monitor runs of deployed models, without leaving Excel. A Deployment Wizard guides users through “point and click” options that make optimization, simulation and machine learning models available to run live in popular tools like Microsoft Teams, Power BI and Tableau. No code is required – but developers can step in and modify JavaScript code to easily extend these cloud apps at any stage.

Even a Monte Carlo simulation model, built with a competitor product that works only in desktop Excel, can be easily converted to Analytic Solver (in Excel desktop or cloud), then auto-translated to RASON, or “used as-is” as an Excel workbook on the RASON cloud server, managed as a RESTful cloud service.

More Optimization, Simulation and Data Science Enhancements

Analytic Solver users constantly receive major functional and performance enhancements for analytic modeling. Besides new features in this release, in the past year users have received new versions of four large-scale Solver Engines for optimization, 15 new PSI Simulation functions for easier use of time series simulation methods, 9 new PSI Optimization functions for live sensitivity results on worksheets, and multi-stage “data science flows” with a drag-and-drop editor in Analytic Solver, plus deployment to the RASON cloud service.

Recommended ITech News: InvoiceCloud and ESC Partners Combine Forces Delivering Online Payment Capability to Public Utilities and City Governments

Related posts

Polygraph Warns Advertisers Not To Rely On IP Blocking To Prevent Click Fraud

CIO Influence News Desk

SmartCow Releases AI-Enabled Controller Ultron Powered by NVIDIA Jetson Platform for Smart Cities and Autonomous Infrastructure Deployments

PR Newswire

Red Hat Introduces Red Hat Trusted Software Supply Chain

Business Wire

Leave a Comment