ToolsGroup is First to Raise Demand Forecasting Accuracy by Embedding Machine Learning Technology

Boston, March 4, 2014 – ToolsGroup, a global provider of market-driven demand analytics and supply chain optimization software, is the first vendor in its class to embed machine learning into a commercially available demand forecasting product. The new technology has been proven to significantly improve forecast accuracy in major global customer installations (see below).

Forecast accuracy is an important driver of business outcomes. Analyst firm Gartner writes, “Benchmarking data of 70 supply chains across multiple industries shows the best forecasters gaining the following: 15% less inventory, 17% stronger order fulfilment and 35% shorter cash-to-cash cycle times.” (Gartner How Good Is Your Forecast? by analysts Noha Tohamy and Debra Hofman, published February 11, 2011).

Yet most demand forecasting systems today often produce disappointing results and significant forecast errors. The standard models found in these systems cannot easily identify trends in the data. Their inability to model the underlying causes of demand variability can also lead to poor trade promotion execution and failed new product launches. And they can be manually intensive, resulting in poor planner productivity.

A data-driven approach using more intelligent software has been shown to improve forecasting accuracy. ToolsGroup’s innovation is to embed machine learning technology into its SO99+ forecasting solution to solve problems that planners face every day and yet have vexed organizations for a long time. It harnesses the power of machine learning to accurately model demand in difficult forecasting scenarios such as trade promotions, new product introductions, extreme seasonality and product cannibalization.

Machine learning takes demand forecasting to new heights because older technologies didn’t solve the difficult problem of measuring the impact of external stimuli on baseline demand.

ToolsGroup’s demand modeling creates a reliable baseline, then uses machine learning to adjust the baseline by identifying the effect of stimuli and demand indicators at a detailed channel level. It analyzes all the relevant variables and the complex interactions among them in a highly automated fashion.

ToolsGroup’s machine learning technology creates a major improvement in demand visibility, forecast quality and level of forecast detail, which are all critical for reliable supply chain planning. It has already been successfully deployed in the forecasting process of multiple clients, including:

• Leading heating and air conditioning (HVAC) manufacturer Lennox deployed it to sift through hundreds of thousands of SKU-Locations to identify “clusters” of those with similar seasonality profiles. Defining seasonality groups for forecasting was very challenging due to many slow moving parts, diverse demand behaviors, and an extremely seasonal business. Machine learning has allowed Lennox to automate the process and create an improved inventory mix over its large distribution network.”By enhancing our seasonality clusters, machine learning substantially increased our peak period forecast accuracy and improved our supply chain responsiveness during a period of strong growth,” according to Keith Nash, Vice President, Supply Chain Logistics, Lennox Residential.
• A multi-national food company deployed it to identify the effects of promotional and media events. Its trade promotion forecasting covered a wide range of fresh products characterized by dynamic demand, short shelf life and the need for accurate demand forecasting. The project resulted in a 20% reduction in forecast error, 30% reduction in lost sales, and a 10 point ROI improvement in promotions.
• Other ToolsGroup customers are using machine learning for new product introduction (NPI) to identify which new products will have significantly above average sales. Identifying those successful new products early on allows companies to determine the most advantageous way to allocate additional marketing, purchasing and replenishment resources to “up and coming” products.

ToolsGroup CEO Joe Shamir said: “After pioneering machine learning to enhance demand forecasting, we are excited to have taken the next step to embed this technology into our standard product footprint. We are proud to be the first supply chain planning vendor to offer a seamless solution to improving demand planning and forecast accuracy through this new technology.”

ToolsGroup’s embedded machine learning is available as part of its SO99+ version 7.3.1 demand forecasting solution. An embedded approach also has the benefits of shrinking the software footprint, integrating the forecasting process, and offering users a standardized solution.