Inspiration
To say that Customer Satisfaction is an understatement. Studies have shown that 80% of marketers view Customer Satisfaction as the main competition area. We are trying to make it more convenient for CBRE to improve Products and Services, monitor brand reputation and decrease churn by using Machine Learning to understand the impact of reviews and comments.
What it does
It uses Machine Learning to extract insights from the public data (surveys, contact centers, and social media) to suggest ideas to improve services, Customer Experience, and maintain brand reputation.
How we built it
We considered a real-world CBRE reviews and processed them by running ML algorithms on them to gauge customer sentiment and recommend better ways to enhance customer experience.
Challenges we ran into
One of the key challenges was to process data i,e. remove noise, perform feature-engineering, and tune it as per the required needs of the model.
Accomplishments that we're proud of
We were able to conceive this model from scratch using real-time data all the way to production abstractly within a short time bound.
What we learned
Firstly, we learnt a great deal about the impact of Machine Learning and the way CBRE implements it in their day to day operations to ensure good customer experience and satisfaction.
What's next for Scrutiny for CBRE
- To facilitate working with real-time more complex dynamic data
- Integrate Scrutiny for CBRE with more convoluted models, such as BERT.
- Furnish more insights for a set of given data.
Log in or sign up for Devpost to join the conversation.