As the global leader in powersports, Polaris Inc. (NYSE: PII) pioneers product breakthroughs and enriching experiences and services that have invited people to discover the joy of being outdoors since our founding in 1954. Polaris’ high-quality product line-up includes the Polaris RANGER®, RZR® and Polaris GENERAL™ side-by-side off-road vehicles; Sportsman® all-terrain off-road vehicles; military and commercial off-road vehicles; snowmobiles; Indian Motorcycle® mid-size and heavyweight motorcycles; Slingshot® moto-roadsters; Aixam quadricycles; Goupil electric vehicles; and pontoon and deck boats, including industry-leading Bennington pontoons. Polaris enhances the riding experience with a robust portfolio of parts, garments, and accessories. Proudly headquartered in Minnesota, Polaris serves more than 100 countries across the globe Polaris.com.
“Incorporating AI into our planning and forecasting through the OneStream Sensible ML solution accelerates the forecasting process and further elevates it with powerful ML data-driven forecasts. Sensible ML forecasts have shown to be more accurate and the value add dashboard enables the business users insights into the key features driving the forecast to easily manage, improve and enhance the model.”
—Melanie Hermann, Director, Finance Process & Systems, Polaris, Inc.
Download the Case Study
In recent years, COVID-19 and global supply chain turmoil have led to an inverted supply/demand model for Polaris. Prior to these disruptions, the company’s production and shipments were coordinated based on innovation and market demand. However, since these disruptions occurred, the business environment became constrained by supply. The Polaris Finance team recognized they were facing a fast-changing business environment that required more speed and agility in planning and forecasting to stay ahead. Sensible ML offered the Office of Finance a solution that can react to these increasingly complex market changes.
Prior to implementing OneStream, Polaris’ business units had relied on a highly manual financial planning model with inputs such as SIOP-generated shipped unit forecasts by product, product costs and MSRPs, freight cost, and dealer discounts to arrive at a gross margin view. This model was referred to as the “Driver-Based Revenue Model,” and it provided the perfect opportunity to incorporate machine learning-driven forecasting and transition to a unified planning process within OneStream.
With 15+ ERP systems in use across the enterprise, Polaris had been using Oracle Hyperion Financial Management (HFM) and Hyperion Planning for financial close, consolidation, planning, financial and management reporting. The Finance team was growing increasingly frustrated with having to move data between one HFM and four Hyperion Planning applications and the associated overhead of maintaining meta data across all five applications. The administration burden of the Oracle application suite was growing and gaps started to develop as the organization grew and changed over time. Polaris started evaluating options for more integrated, robust and flexible system that would grow with their organization. Polaris selected OneStream in 2018 and kicked off their implementation in 2019.
In 2019, Polaris implemented and went live with OneStream for financial consolidations, as well as financial and external reporting. In 2020, the team extended their OneStream implementation to support FP&A as well as management and earnings reporting. Then in 2021, the team implemented OneStream’s Account Reconciliations as well as its Analytic Blend capabilities for increased insight into product data at the VIN and customer level.
After establishing that solid financial platform framework, Polaris continued their OneStream journey, extending the application to support BU checklists, capital reporting and planning, expanding management allocations, focusing on expanded data insights and process automation. They later joined the technical preview program for OneStream’s Sensible Machine Learning (ML) solution.
For the technical preview, Polaris decided to focus their Sensible ML project on their North American Off-Road Products GBU, looking at a 12-month forecasting time horizon with a focus on variables impacting their Shipped Units forecast. These variables included Commodity Prices, Presold Orders, “Clean Build” Percentage and Build-to-Ship Durations. Historic data representing these variables would be combined with historic shipped units to generate the ML models and their forward-looking forecasts. The historic data model covered 181 products, with weekly units sold from 2016 through 2022. Sensible ML crunched through this data, combined with commodity prices for steel and aluminum, factored in events such as holidays, and generated over 2,800 models for comparison. The OneStream ML models proved to be the most accurate, based on the historic data. The ML forecasts were run monthly and were incorporated into a driver-based forecast.
The results of the project with Sensible ML were impressive. Not only were the forecasts more accurate than with prior approaches, but Sensible ML added speed and efficiency to the forecasting process at Polaris, reducing forecasting cycles from days to hours. Sensible ML also provides more transparency into what’s behind the ML models, including insights into the key forecast drivers for more informed decision-making. It provides a finance-run ML forecasting process that integrates seamlessly with the financial planning and forecasting process Polaris supports, all through the unified OneStream platform.
“The ability to quickly generate driver-based forecasts is essential to adapting to our changing business conditions,” said Melanie Hermann, Director, Finance Process & Systems at Polaris Industries. “Incorporating AI into our planning and forecasting through the OneStream Sensible ML solution accelerates the forecasting process and further elevates it with powerful ML data-driven forecasts. Sensible ML forecasts have shown to be more accurate, and the Value-Add Dashboard provides the business users with insights into the key features driving the forecast to easily manage, improve and enhance the model.”
The Polaris Data Science team was impressed with the process and results. “Sensible ML commoditizes the part of my job that can be commoditized and allows me to focus on where I can add value… with the output that Sensible ML provides,” said Luke Bunge, Manager Data Science Product. “It’s an incredible timesaver and gets you to the best answer possible. The team did a great job immersing us in the tool…as opposed to turning it into a black box.”
Polaris has initiated the transition from Private Tech Preview into a fully adopted and productionized Driver-Based Revenue financial planning model powered by Sensible ML. With this transition, the company is already looking at ways to drive further value, accuracy, and transparency with Sensible ML. Polaris is seeking an expanded line of sight by shifting to an extended forecast horizon. In addition, Polaris is progressing with the collection and storage of an additional set of 20 – 30 economic features (or variables) and a series of company and promotional events to plug into Sensible ML.
Download the Case Study