Building a Data-Centric Culture at DoorDash

Author: Rahul Chaudhary

In a recent conversation with Jessica Lachs, VP of Analytics and Data Science at DoorDash, critical insights emerged about building and scaling a data organization that aligns with business objectives.

Metrics and Their Impact

Jessica emphasizes that analytics should drive business impact rather than merely serve as a support function. Companies often focus on answering “why”—analytics should also address “what do we do now that we know this?” Effective metrics facilitate this process.

The Right Metric is Often a Proxy

Retention is often a poor metric for goal-setting because it’s challenging to drive meaningfully in the short term. Jessica advocates for identifying short-term metrics that serve as proxies for longer-term outcomes. For example, instead of directly targeting improved customer retention, one could focus on customer acquisition cost or first-order profitability as a more actionable goal.

Centralized vs. Embedded Structures

Jessica provides a detailed rationale for a centralized analytics structure. Here are the main points:

1. Talent Consistency: Centralizing data functions allows maintaining a consistent talent bar. Jessica believes this consistency breeds performance as teams utilize the same evaluation criteria across all hires.

2. Growth Opportunities: A central structure enables team members to have visibility into opportunities across the entire organization rather than being confined to a specific business unit, which can lead to stagnation.

3. Methodological Consistency: Under a centralized approach, teams can share methodologies and metrics, which enhances collaborative problem solving. This reduces redundancies.

4. Team Culture: A centralized team fosters a sense of belonging and camaraderie. Team members learn from each other’s experiences and are not siloed within their respective departments.

The Importance of Qualitative Research

In conjunction with quantitative data, Jessica underlines the necessity of gathering qualitative insights. By interacting directly with customers through phone calls, data scientists can identify issues that may not surface through standard analytics. For instance, she recounted instances where the data revealed low engagement via referral programs, but further inquiry unveiled considerable fraud that skewed the results.

Balancing Exploration and Execution

Jessica suggests carving out time for exploratory work. A hackathon, where teams dedicate time to innovative projects, could yield actionable insights that drive future business strategies. When teams explore questions beyond day-to-day metrics, they often unlock unexpected opportunities.

The Pitfalls of Composite Metrics

Another key takeaway is the danger of complex composite metrics, which are often confusing. Jessica recommends simplicity—metrics that are intuitive and actionable. For example, she previously oversaw a complex Merchant Health Score that included multiple factors but found it was more beneficial to track a few essential inputs like “order within first seven days.” Keeping it straightforward enables the team to “see what’s important” and act on it effectively.

Best Practices for Hiring

When hiring for the analytics team at DoorDash, Jessica looks for:

• Curiosity: Individuals who naturally seek the underlying problems rather than just answering predefined questions.
• Problem-solving Skills: Candidates must demonstrate an ability to think critically under ambiguous conditions and to pivot based on new information.

Leveraging AI in Analytics

Jessica doesn’t shy away from AI’s role in enhancing productivity. Tools like “Ask Data AI” assist team members in formulating SQL queries. By empowering non-technical staff, DoorDash can optimize productivity and focus analytics resources on strategic initiatives rather than repetitive data retrieval tasks.

Final Thoughts on Data Strategy

Jessica leaves us with her primary insights on what makes a strong data organization:

• Align metrics with business outcomes. A focus on the right proxies can clarify goals.
• Simplify metrics to ensure clarity. Individuals should understand what they are driving towards.
• Encourage a culture of curiosity and exploration. From hackathons to encouraging exploratory research, this fosters innovation and team engagement.

Jessica Lachs’s approach at DoorDash offers a pragmatic lens through which organizations can grow their analytics capabilities and integrate data-driven decision-making into their core.