Predictive Customer Support
Solving Customer Issues on the First Call
Challenges
When a consumer or business has support issues they can end up on the phone with multiple support agents for what seems like hours. For many customers this still will not result in a solution and then a service technician will be dispatched to their location. This process is frustrating for customers who are experiencing phone or internet service issues that are impacting their life or business. This process also impacts support employees who experience low job satisfaction and high turnover.
Opportunity
AI can be used to find patterns in support data to find solutions to customer issues. AI models can utilize a variety of data from prior support inquiries and resolutions, network data, weather data and more. AI models can then determine the most likely issues that the customer is facing with the minimal amount of questioning. This more efficient process is better for customers because their issues are resolved more quickly. The process is better for support agents as they work with fewer unhappy customers and they get to help the customer actually solve their issue. Finally, this process has a huge impact on the bottom line for service providers by reducing the number of unnecessary service technician calls which makes these technical resources available for actual network or hardware repairs.
Why H2O.ai
The mission at H2O.ai is to democratize AI for all so that more people across industries can use the power of AI to solve business and social challenges. Leading telecommunications brands like Comcast have partnered with H2O.ai to deliver the next generation of solutions powered by H2O technologies. H2O Driverless AI is an award-winning platform for automatic machine learning that empowers data science teams to scale machine learning efforts by dramatically increasing the speed to develop highly accurate predictive models. Driverless AI includes innovative features of particular interest to telecom companies including machine learning interpretability (MLI), reason codes for individual predictions, and automatic time series modeling.
Related Case Studies
Bhavana Bhasker, et al.
Data Scientist, Comcast
"We reached 90% accuracy in the real-time deployment and our results were in-sync with the training phase, which was really good."
Lou Carvalheira
Principal Data Scientist, Cisco
"H2O really shines in model training and scoring and we can do it all without sampling the data."