Introduction to Data Science
Download as PPTX, PDF3 likes1,093 views
The document introduces data science, outlining its components such as software engineering and statistical analysis, and provides examples including customer churn rate calculation, regression modeling, and recommender systems. It highlights methods for data gathering, exploration, modeling, and production with practical examples and models. Additionally, it emphasizes the tools and skills needed to start a career in data science, including programming, statistics, and machine learning.
![Example 2: Regression Modeling
Assume X(ni) = [x1, x2, … xk]
f(n) = c1x1 + c2x2 + c3x3 + … + cnxn](https://image.slidesharecdn.com/datascience101-141023225318-conversion-gate02/85/Introduction-to-Data-Science-15-320.jpg)
![Example 2: Regression Modeling
Assume X(ni) = [x1, x2, … xk]
f(n) = c1x1 + c2x2 + c3x3 + … + cnxn
Or, maybe
f(n) = c1x1 + c2x1
2 + c3x2 + c4x2
2 + …+ cmxn
2](https://image.slidesharecdn.com/datascience101-141023225318-conversion-gate02/85/Introduction-to-Data-Science-17-320.jpg)
![Example 3: Recommender Systems
Given customer preferences c[p1,p2,…pn]
and overall rating average roverall
cbias = mean(c[p1], c[p2],… c[pn]) – roverall](https://image.slidesharecdn.com/datascience101-141023225318-conversion-gate02/85/Introduction-to-Data-Science-25-320.jpg)
Introduction to Data Science
- 1. Introduction Sean Byrnes http://seanbyrnes.com @sbyrnes to Data Science
- 2. Who Am I? f ATTENDED FOUNDED CURRENTLY from Yahoo!
- 3. Introduction to Data Science • What is Data Science? • Example 1: Basic Math • Example 2: Regression Modeling • Example 3: Recommender Systems • Getting started in data science
- 4. What is Data Science? Software Engineering + Statistical Analysis
- 5. What is Data Science? 1. Question 2. Data Gathering 3. Exploration 4. Modeling 5. Answer 6. Production
- 6. Example 1: Basic Math What is my customer churn rate? def. Churn rate: The percentage of subscribers to a service that discontinue their subscription to that service in a given time period. (aka attrition rate)
- 7. Example 1: Basic Math # customers at start Churn(month) = # customers lost
- 8. Example 1: Basic Math Month Churn Dec '13 3.75% Nov '13 1.87% Oct '13 3.82% Sep '13 2.76% Aug '13 2.43% Jul '13 2.04% Jun '13 1.60%
- 9. Example 1: Basic Math For all customers acquired in a given month Retention(Cmonth) = Active(Cmonth) Total(Cmonth)
- 10. Example 1: Basic Math 0 1 2 3 4 5 6 Dec '13 100% 12.82% 8.04% 6.34% 4.91% 3.95% 3.14% Nov '13 100% 15.66% 9.97% 6.96% 5.46% 3.88% 2.77% Oct '13 100% 16% 10.86% 8.62% 6.22% 5.06% 3.98% Sep '13 100% 13.28% 9.52% 7.28% 5.28% 4.48% 4% Aug '13 100% 12.96% 9.18% 6.55% 4.73% 3.86% 3.13% Jul '13 100% 15.84% 10.85% 8.27% 6.67% 5.60% 4.63% Jun '13 100% 16.08% 11.36% 8.36% 7.07% 6% 5.25%
- 11. Example 1: Basic Math 0 1 2 3 4 5 6 Dec '13 100% 12.82% 8.04% 6.34% 4.91% 3.95% 3.14% Nov '13 100% 15.66% 9.97% 6.96% 5.46% 3.88% 2.77% Oct '13 100% 16% 10.86% 8.62% 6.22% 5.06% 3.98% Sep '13 100% 13.28% 9.52% 7.28% 5.28% 4.48% 4% Aug '13 100% 12.96% 9.18% 6.55% 4.73% 3.86% 3.13% Jul '13 100% 15.84% 10.85% 8.27% 6.67% 5.60% 4.63% Jun '13 100% 16.08% 11.36% 8.36% 7.07% 6% 5.25%
- 12. Example 2: Regression Modeling How many users will we have next month?
- 13. Example 2: Regression Modeling 160,000 140,000 120,000 100,000 80,000 60,000 40,000 20,000 - 1/1/13 2/1/13 3/1/13 4/1/13 5/1/13 6/1/13 7/1/13 8/1/13 9/1/13 10/1/13 11/1/13 12/1/13
- 14. Example 2: Regression Modeling For data set X(n), find f(n) such that f(ni) ~ X(ni)
- 15. Example 2: Regression Modeling Assume X(ni) = [x1, x2, … xk] f(n) = c1x1 + c2x2 + c3x3 + … + cnxn
- 16. Example 2: Regression Modeling 160,000 140,000 120,000 100,000 80,000 60,000 40,000 20,000 - 1/1/13 2/1/13 3/1/13 4/1/13 5/1/13 6/1/13 7/1/13 8/1/13 9/1/13 10/1/13 11/1/13 12/1/13 Linear Model
- 17. Example 2: Regression Modeling Assume X(ni) = [x1, x2, … xk] f(n) = c1x1 + c2x2 + c3x3 + … + cnxn Or, maybe f(n) = c1x1 + c2x1 2 + c3x2 + c4x2 2 + …+ cmxn 2
- 18. Example 2: Regression Modeling 160,000 140,000 120,000 100,000 80,000 60,000 40,000 20,000 - 1/1/13 2/1/13 3/1/13 4/1/13 5/1/13 6/1/13 7/1/13 8/1/13 9/1/13 10/1/13 11/1/13 12/1/13 2nd Degree Polynomial Model
- 19. Example 2: Regression Modeling 160,000 140,000 120,000 100,000 80,000 60,000 40,000 20,000 - 1/1/13 2/1/13 3/1/13 4/1/13 5/1/13 6/1/13 7/1/13 8/1/13 9/1/13 10/1/13 11/1/13 12/1/13 4th Degree Polynomial Model
- 20. Example 2: Regression Modeling https://github.com/sbyrnes/Lyric
- 21. Example 3: Recommender Systems What other products might this customer buy?
- 22. Example 3: Recommender Systems Product 1 Product 2 Product 3 … Product N Customer 1 3.5 4.0 3.0 Customer 2 2.0 3.5 Customer 3 3.0 2.5 … Customer N 4.5 4.5
- 23. Example 3: Recommender Systems Given customer preference matrix M, find P x Q ~ M
- 24. Example 3: Recommender Systems Product 1 Product 2 Product 3 … Product N Customer 1 3.5 4.0 2.5 3.0 Customer 2 2.0 1.5 3.5 3.0 Customer 3 1.5 3.0 2.5 4.0 … Customer N 4.5 3.5 4.0 4.5
- 25. Example 3: Recommender Systems Given customer preferences c[p1,p2,…pn] and overall rating average roverall cbias = mean(c[p1], c[p2],… c[pn]) – roverall
- 26. Example 3: Recommender Systems https://github.com/sbyrnes/likely.js
- 27. Getting Started in Data Science • Programming • Statistics • Machine learning • Toolkit – R – Hadoop – D3
- 29. Sean Byrnes seanbyrnes.com @sbyrnes github.com/sbyrnes