Call Center Optimization for a Medical Tourism Marketplace

by Max Frolov
CEO @ DataRoot Labs
Client Services:
Tech Stack:
Python
TensorFlow
Apache Kafka
Apache Beam
PostrgeSQL
Jenkins
Docker
Industry:
Healthcare
Project Length:
2 months
Read independent verified review on Clutch.co


Summary

  • Bookimed is a leading medical tourism marketplace that connects prospect patients with the most fitting medical providers worldwide. The call center department operates as a backbone of the business providing voice consultations to interested patients while adding a human touch to the interaction with the online platform.
  • The doctors or "coordinators" working at the call center, process on average 30-40 applications per day. Prospects come with various preferences and expectations. Not every caller is interested in a treatment - sometimes they need only the information. Other patients require a special approach offered by experienced coordinators only.
  • The company tasked our team with automating part of the routine work of coordinating doctors by identifying the psychotype of a prospect and matching them with the right coordinator at the call center.

Tech Challenge

  • We had to build a scalable recommendation engine based on deep learning model that would increase the conversion of prospects to customers by matching them with the right coordinator at the call center.
  • The pairs are formed based on prospects' medical needs, clinic location and treatment preferences, their behavior on the website and the skillset of the coordinator to convert such prospect into a client.
  • Those recommendation are revenue driven, maximizing profits of the service, while providing high quality services to a patient.

Solution

  • Recommendations are processed in real-time and allow coordinators to tailor their approach to prospect patients while providing them with the highest standards of service.
  • Built from scratch, the solutions is an individual customizable recommendation engine, which takes into account hundreds of parameters coming from client’s analytics engine.
  • Model was trained on Tensorflow and exposed with TF Serving.

Impact

  • The recommendation engine built by our team is like "Uber for medical tourism" solution.
  • Today it is the essential part of the daily work of the coordinators at the Bookimed call center. The solution has won coordinators' trust and performs in line with coordinators’ experience and expectations.
  • Bookimed has raised funding from a leading VC firm and currently ranks among top three marketplaces in medical tourism niche globally.

Updated Aug 13, 2019 — 13:00 UTC

Read Next

Data Visualization with Tableau • 13 Jun 2018 • 7 min read

Media Plan Performance Analytics Platform • 02 Jul 2019 • 4 min read

Candidate Scoring Models for a Job Search Platform • 29 Jul 2019 • 3 min read

AI-Powered Automation of SEO Analytics for a Digital Agency • 08 Jul 2019 • 3 min read

Real-time Insurance Credit Score Modeling • 24 Jul 2019 • 3 min read