AI/NLP Insights
Resources
>
Case Study
>
AI/NLP Insights
Business Problem
A travel recommendation engine wants to provide Travel Personalization and Review Intelligence solutions that enable hotels, hospitality consultants and OTAs to measure and enhance their products & services, improve their reputation and promote guest satisfaction.
Requirements
- Aggregate and analyze online customer reviews to recommend meaningful and actionable insights for the hospitality industry.
- Constantly rank reviews from different sources with varying weightage.
Challenges
- Natural Language processing in different languages.
- Building hospitality taxonomy and constantly training models.
Solution
- Designed, built, and operated core Machine Learning and Lexical Analytics platform using Stanford NLP and custom algorithms.
- Build region specific overrides and multi-tier taxonomy for better accuracy.
- The underlying ML-Ops platform provides all the necessary tools for data scientists to put their best model into production.
- Implemented ML models and Deep learning models with experimentation.
Business Outcomes
13% : Increase in Hotel occupancy.
30% : Recommendation relevancy.
Tech Stack
- Custom Algorithms
- Stanford NLP SciKit
- PyTorch
- Keras
- TensorFlow
- OpenCV
- Python
- Docker
- Data Visualization
- custom charts
- Casandra
- AWS Native