AI developers DataRobot and Palantir Technologies Inc have entered into a new partnership designed to create unique, agile and real-time solutions to help solve the most pressing demand forecasting problems.
Demand forecasting models are often outdated, rigid, and poorly equipped to deal with change. The speed in which supply chains, consumer demand, and shipping logistics have changed over the past year has forced organisations to rethink their approach when it comes to demand forecasting for the future. To support retailers in managing this challenge, DataRobot and Palantir have partnered to create a custom, newly developed framework that will empower companies to take on a more nimble strategy to demand forecasting, eliminating the time and resources spent on manual data cleansing and one-off manual modeling.
The framework combines the best of Palantir Foundry and DataRobot model development capabilities to give customers the ability to create and test data-driven, easily updated forecasting models in minutes, not months, from a single platform. With a holistic view of the retail ecosystem, brands will be able to avoid previous blind spots, and make better and more impactful business decisions.
“As per our 2021 global BuyerView study, 35% of businesses cite limited AI expertise and 33% cite increasing data complexities and silos as barriers to successful AI adoption. Traditional demand forecasting models are getting outdated because of the increased amount of data generated from businesses and external sources,” said Ritu Jyoti, Program Vice President, WW AI and Automation Research Practice at IDC.
Jyoti continued: “With the help of rich datasets and implementation of modern machine learning algorithms into businesses’ supply chain management, companies can improve the accuracy of forecast results and optimise their replenishment plans. This new partnership brings together complementary solutions and will help retail customers unlock the transformative power of AI, for example improved forecast accuracy will lead to reduction in lost sales due to inventory out-of-stock situations and help warehousing costs decrease.”
To create and execute these models, the solution leverages Palantir Foundry’s Software Defined Data Integration to integrate multiple massive scale existing data sets, rapidly creating a high-quality data asset. This integrated data asset is then fed into DataRobot’s Augmented Intelligence technology, which trains and produces hundreds of forecasting models in the time it would take a data scientist to produce one. DataRobot’s unique ability to develop Time Series models and combine multiple data types into model development dramatically enhances the ability to forecast demand.
The best models are then brought back into Foundry and infused into operational workflows, delivering massive scale data and AI to business users. The models are constantly updated and trained by DataRobot to keep them relevant and fed back into the organisation’s integrated data asset. Future modeling becomes even faster, allowing each subsequent project to take advantage of Foundry’s data asset and previous modeling outcomes.
“This partnership brings together the best of both companies' offerings, and we are excited to see what our customers are able to do with this new solution,” said Shyam Sankar, COO of Palantir Technologies. “At Palantir, we tell our customers when they upgrade their software, they upgrade their business and this partnership profoundly speaks to that reality: upgrading your demand forecast upgrades inventory planning, pricing and promotions, logistics, production, and so much more.”
“The pandemic completely upended the way our customers forecast demand, which is why we’ve partnered with Palantir to ensure they can create the most accurate, viable models moving forward,” said Dan Wright, CEO of DataRobot. “By combining the power of the DataRobot Augmented Intelligence platform with Palantir’s capabilities, we’re helping our joint customers create longer lasting, more flexible AI solutions that will generate tremendous business value.”