Deep learning coming to the tire industry: Warehouse staffing with RNN-LSTMs and pricing optimizations with DNNs





Who is this presentation for?
- Data scientists, data engineers, data architects, and directors of data science
Level
IntermediateDescription
Deep learning has been a sweeping revolution in the current world of AI and machine learning. It uses convolutional neural networks (CNNs) to help Teslas see the road properly; it uses reinforcement deep learning to help SpaceX land rockets automatically, and it uses recurrent neural networks (RNNs) to make machines translate better. The list goes on and on. But traditional industries may not see how this new, hot technology can help them.
Alex Liang details how the data science team at American Tire Distributors (ATD) uses machine learning solutions to rejuvenate the company. He used LSTM RNN models ensembled with fbProphet to generate staffing-level forecasts and further optimized with CVXPY for maximum optimality of staffing schedules. He also implemented deep neural nets as part of a pricing optimization pipeline, where DNNs are used for clustering as well as product demand modeling. The warehouse solution is now being used every day across the entire US in 140 distribution centers to cost-effectively staff more than 2,000 people daily and is on track to realize ~10% in labor cost savings and the pricing solutions are now being fully productionalized into the revenue management process, automating and optimizing pricing decisions for the majority of products. He outlines the overall business problem context, initial machine learning prototyping, resolving challenges in data and compute, and application automation. You’ll leave with key takeaways in developing this solution, including both technical and business lessons.
Prerequisite knowledge
- General knowledge of deep learning
- Experience with Python and data technologies (SQL, databases, and Hive)
- Familiarity with cloud computing concepts
What you'll learn
- Understand that any traditional industry can improve its business processes and create concrete values with open source technologies, cloud computing platforms, current cutting-edge deep learning, and AI techniques

Alex (Tianchu) Liang
American Tire Distributors
Tianchu Liang is a principal data scientist with American Tire Distributors. He’s a physicist and mathematician turned computer scientist turned machine learning enthusiast. He develops and deploys machine learning solutions to solve real world business problems, such as using LSTM to forecast staffing needs and using XGBoost models to execute real-time online customer behavior classifications. As one of the first two data scientists in company history to join American Tire Distributors, he helped grow the data science team to a size of 12 within a year and is now developing machine learning solutions to help the company in supply chain, sales, and warehousing, as well as ecommerce.
Comments on this page are now closed.
Presented by
Elite Sponsors
Strategic Sponsors
Diversity and Inclusion Sponsor
Impact Sponsors
Premier Exhibitor Plus
R & D and Innovation Track Sponsor
Contact us
confreg@oreilly.com
For conference registration information and customer service
partners@oreilly.com
For more information on community discounts and trade opportunities with O’Reilly conferences
Become a sponsor
For information on exhibiting or sponsoring a conference
pr@oreilly.com
For media/analyst press inquires
Comments
Most AI talks are about applications in tech, software, ecommerce, maybe finance or health; but there are so many other industries, ripe for AI revolution. If you want to know how we apply deep learning solution in a traditional industry, come to this session. I will talk about the challenge we faced, both from data and business adoption, the solution we developed, and some other lessons and general thoughts about applying AI.
Implementing state of the art deep learning models is hard, put those models into production and scale up is harder, getting the business buy-in and put deep learning to generate real business value is even harder. And this is the main challenge faced by non-tech industries when applying AI. In traditional industries, data is messy, tech infrastructure tend to be outdated, and people’s mindset requires change, how do we apply cutting machine learning and push for business impact? Come to this session to find out.