Time Series Data Prediction for Service Ops

Lu Yan
LINE Fukuoka / Data Science Team / Data Scientist

https://linedevday.linecorp.com/2021/ja/sessions/22
https://linedevday.linecorp.com/2021/en/sessions/22
https://linedevday.linecorp.com/2021/ko/sessions/22

Transcript

2. Agenda - Project Background & Members - Overview of In-House Time Series Prediction Tool - Achievements and Future Prospects
3. Project Members Lu Yan Data Scientist Terry So Machine Learning Engineer Yuan Yifan Machine Learning Engineer
4. Typical use case for user inquiry form à User buys new iPhone à Has problem transferring LINE account to the new device à Contact LINE via an inquiry form Project Background
5. Project Background a Typical Use Case LINE Fukuoka Data Scientist Team + Value Management Center < Inquiry Count Forecasting> How many users’ inquiries do we need to treat for each LINE service every month? Every day? Every hour?
6. Project Background Motivation for Developing a Forecasting Tool - Dozens of predictions required every month for different departments - High project communication cost - Limited number of Data Scientists - Relatively similar data structure - Many repetitive operations of data pre-treatment and model training
7. Project Background - Develop a tool for both Data Scientists and non-Data Scientist users from LINE biz/operational service department - For non-DS(non-Data Scientist) users - Let users do the forecast by themselves - For DS(Data Scientist) - Automate repetitive steps Motivation for Developing a Forecasting Tool
8. For non-DS For DS Project Background Tool Design
9. Agenda - Project Background & Members - Overview of In-House Time Series Prediction Tool - Achievements and Future Prospects
10. Main Components of the Tool Add Dataset Train the model Forecast Add Project Overview of In-House Time Series Auto Prediction Tool
11. Main Components of the Tool - Project Overview of Tool – for non-DS User
12. Main Components of the Tool Add Dataset Train the model Forecast Add Project Overview of In-House Time Series Auto Prediction Tool
13. Main Components of the Tool – Dataset Overview of Tool – for non-DS User - Supports different kind of data sources (CSV, MySQL, Presto, Spark SQL etc.) - Connects to internal DB - Provides anomaly detection and imputation function
14. Main Components of the Tool – Dataset Overview of Tool – for non-DS User
15. Main Components of the Tool Add Dataset Train the model Forecast Add Project Overview of In-House Time Series Auto Prediction Tool
16. Main Components of the Tool - Predictor Overview of Tool – for non-DS User - Different types of models (Prophet, LSTM, ARIMA, Temporal Fusion Transformers etc..) - Hyperparameter Tuning - Model Explanation - Model Evaluation (RMSE/MAPE/WAPE etc..)
17. Main Components of the Tool Add Dataset Train the model Forecast Add Project Overview of In-House Time Series Auto Prediction Tool
18. Overview of Tool – for non-DS User Main Components of the Tool - Forecast
19. - Runs Python client - Supports batch jobs - Provides advanced functions - Keeps adding new features Overview of Tool – for Data Scientist
20. Overview of Tool – for Data Scientist Batch Jobs
21. Overview of Tool – for Data Scientist Advanced Functions Examples – Hyperparameter Tuner
22. Overview of Tool – for Data Scientist Advanced Functions Examples – Model Explanation
23. Overview of Tool – for Data Scientist Advanced Functions Examples – Model Explanation
24. - Support usage of standard SQL queries to run the model and to do the prediction Overview of Tool – for Data Scientist Keep Adding New Features – SQL-Like Syntax
25. Overview of Tool – for Data Scientist Keep Adding New Feature - Show Past Predictions
26. Overview of Tool System Architecture
27. Overview of Tool System Architecture Django Framework – Web API
28. Overview of Tool System Architecture Celery – Distributed Task Queue
29. Overview of Tool System Architecture Elasticsearch - Log System
30. Agenda - Project Background & Members - Overview of In-House Time Series Prediction Tool - Achievements and Future Prospects
31. Achievements and Future Prospects Quantity of prediction tasks + High project communication cost VS Limited number of Data Scientists Repetitive operations of data pre- treatment and model training DS can take advantage of the API & advanced functions and can run batch jobs easily Non-DS Users can do predictions by themselves with the UI and functionalities developed Use Case with Value Management Center
32. Achievements and Future Prospects Use Case with Value Management Center - Use case – Inquiry Count Forecasting - After the usage of this tool, the work time has been reduced by 83% - The accuracy of prediction is higher and more stable, regardless of seasonality and personnel change. Source :https://linefukuoka.blog.jp/archives/20210630_01_news_plan_and_op.html
33. Achievements and Future Prospects - Open to more business departments - Improve UI - Support more types of data visualization - Allow users to select weather/holiday common features - Support multi-horizon forecast Future Prospects
34. Thank you