Scrap it regularly in the business domain of Tourism
Project Profile
Compensation of errors in signaling data by making the relevance evaluable with alterative measurement (Google waiting times). Born from the need of data acquisition, the approach to realize a data acquisition for Common Data /Frequent Data usage with simple means.
At a glance - essential project data
| Duration | From 5/1/2019 to 5/31/2019 with about 1 months of full engagement | |
|---|---|---|
| Data and Tools | Market - Tourism Sources • Google Search API • Google Places • Scraping dynamically the requested 3000 Locations • Every new location is requested upon API Call | |
| Integration | • Runs on a Rasperry PI (Low Energy Consumption!) • Aggregates 3000 Location Data since 06/2019 • Coverage of Locations Continuously providing a simple API for Customer Requests (CMS/Location Database) | |
| AI Methods | • Python (deep ?) tricks • ML and Statistics |
Engagement Use-Case
Searching waiting times, opening hours for data mining to populate central systems.
Client motivation / Solution aims
- Simple data mining for ML models to predict waiting times in POIs (as alternative for transaction data)
AI Approach
| AI key technology used in our solution | Statistically enhancing of the Google API for standard usage | |
|---|---|---|
| Solution Approach | ML | |
| Project Approach | Simply agile | |
| Project Type | Project | |
| ML Integration and ML Operations | • Operation Integration • Rasperry PI |
Insights and Details
Simple scrapping of commonly available information
