In this episode, we will discuss the machine learning architecture built by LinkedIn for their premium product recommendation. We will explore the machine learning architecture, which includes a two-towered neural network and reinforcement learning as key components.

For more details, you can refer to their published tech blog, linked here for your reference: https://www.linkedin.com/blog/engineering/machine-learning/matching-linkedin-members-with-the-right-premium-products

In this episode, we will discuss why search relevance is important for Faire, how their data team quantifies semantic relevance in search, and how they leverage large language models (LLMs) to measure it efficiently.

For more details, you can refer to their published tech blog, linked here for your reference:
https://craft.faire.com/fine-tuning-llama3-to-measure-semantic-relevance-in-search-86a7b13c24ea

In this episode, we will touch on the importance of A/B testing in the product decision-making process. We will share the four types of metrics and the decision-making framework used by the Data Science team at Spotify, as well as the necessary statistical adjustments that need to be incorporated into experimentation to ensure a solid statistical foundation.

For more details, you can refer to their published tech blog, linked here for your reference:
https://engineering.atspotify.com/2024/03/risk-aware-product-decisions-in-a-b-tests-with-multiple-metrics/ 

In this episode, we will discuss the importance of Estimated Time of Arrival (ETA) for DoorDash and how the company enhanced its machine learning model through three key directions: upgrading from a tree-based model to a deep-learning architecture, adopting a multi-task modeling approach, and leveraging probabilistic models.

For more details, you can refer to their published tech blog, linked here for your reference: https://doordash.engineering/2024/03/12/improving-etas-with-multi-task-models-deep-learning-and-probabilistic-forecasts/

In this episode, we will discuss the intricacy of balancing both the art and science aspects in forecasting. We will explore this through two key aspects: validation of forecasting and integrating product impact into forecasting, where combining the art and science can be crucial to enhancing forecasting performance.

For more details, you can refer to their published tech blog, linked here for your reference:
https://medium.com/@AnalyticsAtMeta/forecasting-meta-balancing-art-and-science-92526e1ae36c

In this episode, we will discuss what is feature selection and how JustEatTakeaway.com leverages generic algorithms as one practice to to optimize their feature selection.

For more details, you can refer to their published tech blog, linked here for your reference:

https://medium.com/justeattakeaway-tech/optimising-feature-selection-with-genetic-algorithms-an-easy-to-use-python-script-dde44cc9c053 

In this episode, we will discuss how to build an effective monitoring mechanism for a recommendation system. We will cover the basic components of various recommendation processes and explore how the Tubi TV Engineering team developed their monitoring flow.

For more details, you can refer to their published tech blog, linked here for your reference: https://code.tubitv.com/how-to-monitor-a-recommender-system-6d720c922c90

In this episode, we will introduce the concept of causal inference, and discuss how the data scientist team from Walmart determines Causal Effects when A/B Tests are Infeasible through Adopter Analysis.

Based on their published tech blog, with the link provided here for your reference:  https://medium.com/walmartglobaltech/how-to-determine-causal-effects-when-a-b-tests-are-infeasible-through-adopter-analysis-b06f2d51a633 

In this episode, we will discuss the importance of metrics for the business. We will share the journey of how Indeed started with a single metric to measure client-side performance, and eventually converged into a composite metric serving as a comprehensive measure

Based on their published tech blog, with the link provided here for your reference: 
https://engineering.indeedblog.com/blog/2024/01/composite-web-performance-metric

In this episode, we will explore how Pinterest uses generative AI technology to develop a text-to-SQL feature for their data analytics team. We will examine the general architecture of their two iterations, regarding how the team has enhanced the AI product to support better a wider range of analytics use cases with improved productivity.

Based on their published tech blog, with the link provided here for your reference: https://medium.com/pinterest-engineering/how-we-built-text-to-sql-at-pinterest-30bad30dabff