Schedule: Retail and e-commerce sessions

Recommendation systems play a significant role—for users, a new world of options; for companies, it drives engagement and satisfaction. Amit Kapoor and Bargava Subramanian walk you through the different paradigms of recommendation systems and introduce you to deep learning-based approaches. You'll gain the practical hands-on knowledge to build, select, deploy, and maintain a recommendation system. Read more.

Each week 275 million people shop at Walmart, generating interaction and transaction data. Navinder Pal Singh Brar explains how the customer backbone team enables extraction, transformation, and storage of customer data to be served to other teams. At 5 billion events per day, the Kafka Streams cluster processes events from various channels and maintains a uniform identity of a customer. Read more.

James Tang, Yiyi Zeng, and Linhong Kang outline how Walmart provides a secure and seamless shopping experience through machine learning and large scale data analysis on centralized platform. Read more.

With ML becoming more mainstream, the side effects of machine learning and AI on our lives become more visible. You have to take extra measures to make machine learning models fair and unbiased. And awareness for preserving the privacy in ML models is rapidly growing. Mikio Braun explores techniques and concepts around fairness, privacy, and security when it comes to machine learning models. Read more.

Fei Wang takes a deep dive into a case study for the CarGurus TV Attribution Model. You'll understand how you can leverage the creation of a causal inference model to calculate cost per acquisition (CPA) of TV spend and measure effectiveness when compared to CPA of digital performance marketing spend. Read more.

Data-driven software is revolutionizing the world and enable intelligent services we interact with daily. Robert Pesch and Robin Senge outline the development process, statistical modeling, data-driven decision making, and components needed for productionizing a fully automated and highly scalable demand forecasting system for an online grocery shop for a billion-dollar retail group in Europe. Read more.

Causal questions are ubiquitous, and randomized tests are considered the gold standard. However, such tests are not always feasible, and then you just have observational data to get to causal insights. But techniques such as matching offer an opportunity to solve this. Subhasish Misra explores this and practical tips when trying to infer causal effects. Read more.

Every data team has to build an ecosystem that sustains the data, the users, and the use of the data itself. This data ecosystem comes with its own challenges during the building phase, maintenance, and enhancement. Neelesh Salian dives into the importance of data lineage for an organization. You'll explore how to go about building such a system. Read more.

Automating decisions require a system to consider more than just a data-driven prediction. Real-world decisions require additional constraints and fuzzy objectives to ensure they're robust and consistent with business goals. Brian Keng takes a deep dive into how to leverage modern machine learning methods and traditional mathematical optimization techniques for decision automation. Read more.

Narvar provides next-generation posttransaction experience for over 500 retailers. Karthik Ramasamy and Anand Madhavan take you on the journey of how Narvar moved away from using a slew of technologies for their platform and consolidated its use cases using Apache Pulsar. Read more.