20
Analyzing Analysts Dustin McIntosh Mode Analytics Understanding the Queriers Behind the Queries

Insight Demo

Embed Size (px)

Citation preview

Page 1: Insight Demo

Analyzing Analysts

Dustin McIntosh

Mode Analytics

Understanding the Queriers Behind the Queries

Page 2: Insight Demo

Goal: Understand user base and how they interact with the product

NovicesPower Users

● Who are the users?

● Which SQL errors do they make?

● How can we make users' experience better?

● Why do users churn?

● Can we personalize product response for different users?

Page 3: Insight Demo

Goal: Understand user base and how they interact with the product

● Who are the users?

● Which SQL errors do they make?

● How can we make users' experience better?

● Why do users churn?

● Can we personalize product response for different users?

NovicesPower Users

Page 4: Insight Demo

Time

Churn – Are users getting frustrated?

Successfulquery

SQLerror

Page 5: Insight Demo

Churn – Are users getting frustrated?

Page 6: Insight Demo

Churn – Are users getting frustrated?

No!

Page 7: Insight Demo

Churning Users = Tutorial Users

Recommendation: prompt tutorial users to connect their own data at tutorial conclusion

Page 8: Insight Demo

Can we personalize product response for different users?

Expert?

Novice?New User

Page 9: Insight Demo

Classifying Experts vs. Novices

Bag of SQL

keywords

Formatting based:

– White space

– Parentheses

Keyword diversity

Is it an Error?

Error type

Random Forest

Page 10: Insight Demo

Bag of SQL

keywords

Formatting based:

– White space

– Parentheses

Keyword diversity

Is it an Error?

Error type

Random Forest

AUC = 0.66

Classifying Experts vs. Novices

Page 11: Insight Demo

The Differences Between Experts and Novices

Page 12: Insight Demo

Summary

● Who are the users?

● Which SQL errors do they make?

● How can we make users' experience better?

● Do users churn out of frustration?

● Can we personalize product response for different users?

Expert?

Novice?

Page 13: Insight Demo

Dustin McIntosh

EFavDB.com

Page 14: Insight Demo

Extra Slides

Page 15: Insight Demo

What errors do they make?

Recommendation: prominently display or auto-correct table/column names

Page 16: Insight Demo

Top-heavy nature of SQL

Page 17: Insight Demo

Non-tutorial users also not getting frustrated

All churned users Churned users that have connected their own data

Page 18: Insight Demo

Correlations of the Features

Page 19: Insight Demo

Compare Using top 5 features

All features

Top 5 features

Page 20: Insight Demo

Histograms of important features

novicesexperts