Open Source in Real Life

Transcript

1. OPEN SOURCE IN REAL LIFE
2. WHAT IS SERENATA?
3. WHAT IS SERENATA? • The main goal: use artificial intelligence to social control of public administration • We learnt how to work with data science using open data (CSVs that show reimbursements). • Multidisciplinary team: Scientists, programers, marketing and journalists • Open Source: More than 700 members in the Telegram group.
4. WHY? • Advantages: Bringing citizens and government closer, suggesting technology solutions • For the developer: tool choice flexibility
5. • We did a crowdfunding campaign that would pay 3 months of development • Data science projects usually take 6 months to a year, what can we do in 3 months? • Techniques: hypothesis driven development and timeboxing HOW DO WE GET HERE?
6. TECHNIQUES
7. • Hypothesis-Driven Development • Survey of hypotheses that seek the solution of a problem • Multidisciplinary team as a way to expand knowledge HDD: HYPOTHESES
8. • List of hypotheses to explore • Associate a time window with development, and if it doesn't work, switch to another hypothesis • Back to previous assumptions as time goes by TIMEBOXING
9. • We studied the available dataset, and by that we defined some hypothesis we could have: ◦ Non-Standard Prices on Food ◦ Traveled distance and spending ◦ Invalid tax identification number ◦ Monthly maximums (taxi, fuel, ...) DEVELOPED HYPOTHESES
10. • Jupyter notebook with initial analysis • Script for parsing the entire database • Training an initial model • Retraining after time period DEVELOPMENT CYCLE
11. DEVELOPMENT CYCLE
12. DEVELOPMENT CYCLE
13. RESULTS
14. MAIN REPO
15. REIMBURSEMENTS DASHBOARD
16. TWEETING ROBOT
17. INSPIRATION FOR OTHER PROJECTS
18. SERENATA.AI/EN @anaschwendler