USING DATA TO DRIVE SUCCESS: Learn how Zulily and Sounders FC get the most out of their metrics!

On Tuesday, September 10th, Zulily was proud to partner with Seattle Sounders FC for a tech talk on data science, machine learning and AI. This exclusive talk was led by Olly Downs, VP of Data & Machine Learning at Zulily, and Ravi Ramineni, Director of Soccer Analytics at Sounders FC.

Zulily and Sounders FC both use deep analysis of data to improve the performance of their enterprises. At Zulily, applying advanced analytics and machine learning to the shopping experience enables us to better engage customers and drive daily sales. For Sounders FC, the metrics reflect how each player contributes to the outcome of each game; understanding the relationship between player statistics, training focus and performance on the field helps bring home the win. For both organizations, being intentional about the metrics we select and optimize for is critical to success.

We would like to thank everyone who attended the event for a great night of discussion and for developing new ties within the Seattle developer community. For any developers who missed this engaging discussion, we invite you to view the full presentation.

For more information, check out our tech blog: https://zulily-tech.com/

Transcript

2. 39 United States Patents Erdös Number 3 Expt. & Theoretical Physics Applied & Computational Mathematics Began Career at Microsoft Research 9 Startups incl. INRIX, Amplero Consultant to >40 global brands
4. Data-driven approaches work, but the impact can be unexpected! The impact is directly related to the metrics you choose to optimize. For long term positive impact the customer experience and your business metrics must align rather than compete.
8. 8 A NEW STORE EVERY DAY INSPIRED, DISCOVERY-DRIVEN EXPERIENCE HIGHLY CURATED A DAILY DESTINATION MASSIVELY PERSONALIZED APPROACH
9. V
10. • • • •
11. Machine Learning Sense Think Act Feedback/Metric Artificial Intelligence
12. Optimizing for Likelihood to Buy Optimizing for Likelihood to Spend Likelihood of Purchase Order Value Profitability
13. • • *Example Data Shown
14. • • Percent of Sort Rankings for which event is in Top 6 Distribution of how event is sorted across all customers Example Data Shown
15. • Cumulative Click-Throughs Day 1 Day 2 Day 3 Example Data Shown
16. Be deliberate in considering the business metric you are trying to impact If you can’t directly connect your experience outcomes to the business metric find a proxy Continually experiment at low business impact before you dive all the way in!
18. USE CASES
19. TYPICAL SOCCER MATCH IN NUMBERS • • • •
20. SCORING GOALS • • • • • •
21. SHOTS METRICS • • •
22. PRIME AREA FOR GOAL SCORING
23. CHANCES • • •
24. DIRECT PLAY • •
25. POSSESSION Text Text • Possession – Advance the ball into opponent half, opponent 3rd and try to find a team mate in the high-value shooting zone. • Higher quality chances, but needs skill and better play to advance the ball through possession
26. PLAYING STYLES AND PLAYERS • • • •
27. SELF-SCOUTING – KNOWING WHO WE ARE • • • •
28. EXAMPLE: ATTACK PAZ (PRIME ASSIST ZONES)
29. ALL THIS SEEMS INTUITIVE AND NOT ROCKET SCIENCE • ☺ •
30. INTEGRATION INTO TRAINING DRILLS •
31. METRICS • • • • • • • •
32. SCOUTING PLAYERS • • • • • • •
33. IN SUMMARY • • • •