MLOps.community
Real-Time Forecasting Faceoff: Time Series vs. DNNs // Josh Xi // #305
Apr 11, 2025
Josh Xi, a Data Scientist at Lyft with a PhD in Operations Research, shares insights on real-time forecasting methods for marketplace dynamics. He discusses the effectiveness of time series models over deep neural networks, emphasizing their adaptability and efficiency. Listeners will learn about integrating external data like weather and events into demand forecasts. Xi also delves into the complexities of geographical forecasting and the role of human insights in enhancing predictive accuracy, making it a must-listen for data enthusiasts!
53:41
Episode guests
AI Summary
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- Time series forecasting methods, favored by Lyft, excel in real-time market adjustments due to their simplicity and interpretability.
- Monitoring and adjusting for forecast errors is crucial for enhancing demand prediction accuracy, ensuring continuous adaptation to market dynamics.
Deep dives
Balancing Supply and Demand
The discussion delves into the complexities of managing supply and demand in a ride-sharing marketplace. To achieve market balance, price adjustments and driver incentives are considered critical levers. The interviewee's team is responsible for creating models that forecast demand and supply, taking into account various signals. These models help inform decisions on pricing strategies and driver incentives, which are vital for maintaining balance across urban regions.
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
