Czech financial savings financial institution Česká spořitelna, a division of Austria’s Erste Group, just lately collaborated with AI answer builder DataSentics to discover the usage of GenAI in name facilities. Česká wished to enhance high quality management and optimize prices of their inbound name middle operations, which obtain round 2 million calls per 12 months. They selected the Databricks Information Intelligence Platform to experiment with each inner and exterior AI fashions to evaluate the effectiveness of name middle brokers.
Exploring a High quality Management System for Buyer Help
The decision middle group at Česká spořitelna wished to check a top quality management system powered by GenAI that may be certain that brokers adhere to scripted pointers throughout buyer interactions. A crucial problem for Ceska was making certain constant agent communication for routine buyer inquiries. When prospects name about account balances, brokers have to direct them to on-line banking options, a key enterprise requirement that drives digital adoption and operational effectivity. The help group wanted a scalable technique to confirm agent compliance and preserve communication requirements throughout 1000’s of buyer interactions. To realize this, the group started by utilizing Whisper, a speech-to-text mannequin from OpenAI, to transcribe conversations precisely. The problem was to supply human-readable textual content that precisely represented spoken phrases utilized by name middle brokers with out distorting their which means. The transcriptions wanted to make logical sense and mirror the intent of the dialog precisely for additional evaluation.
Following the transcription, the group explored integrating each inner GPT fashions and open supply fashions resembling Mixtral to judge their effectiveness. GenAI fashions have been examined in a simulated QA position, the place they have been tasked with answering particular questions resembling “Did the agent redirect the client to on-line banking?”. The purpose of this train was to evaluate how nicely these fashions may mimic human understanding and decision-making when verifying compliance with established pointers. By evaluating the efficiency of each the inner GPT mannequin and the open supply fashions, the group aimed to search out the simplest answer for bettering customer support via automated AI-driven high quality management.
Advantages of the Databricks Information Intelligence Platform for GenAI
The DataSentics group evaluated a number of choices for this answer, and finally selected to deploy the Databricks Information Intelligence Platform and Mosaic AI instruments at Česká spořitelna for a number of causes:
- Information Administration and Governance Advantages: Unity Catalog makes knowledge simply accessible for various fashions whereas maintaining delicate knowledge underneath restricted entry.
- Complete Information Processing Capabilities: the Databricks Platform helps all the workflow of preprocessing of name middle knowledge, from transcription to high quality management. This permits us to supply intermediate outcomes that may be leveraged for different fashions and tasks, resembling advertising and marketing, danger evaluation, regulatory compliance, and fraud detection.
- Mannequin Coaching and Help: Databricks supplies sturdy help and experience for GenAI, together with mannequin structure and coaching capabilities. This made it a really perfect platform for testing and deploying open supply fashions rapidly, enabling us to experiment and iterate effectively.
- Ease of Cluster Creation: With Databricks, it’s easy to create clusters and deploy open-source fashions. This streamlines the experimentation course of and permits us to focus extra on mannequin efficiency and fewer on infrastructure administration.
Insights and Outcomes
All through the challenge, we experimented with numerous segmentation strategies and gathered a number of precious insights:
- High quality of Enter Information is Essential: The standard of the audio recordings different from shopper to shopper, with some talking quietly or from a distance, which may later have an effect on the accuracy of the transcription. Whisper or related programs can assist resolve the issue.
- Class Definition is a Should: We realized that if classes can’t be simply outlined for people, it’s equally difficult for LLMs to grasp them. This bolstered the necessity for clear and exact class definitions to coach the fashions successfully.
- Open-Supply Fashions Ship Outcomes: Open-source fashions demonstrated that they may compete successfully with proprietary fashions like ChatGPT. This discovering is important for companies seeking to optimize prices whereas nonetheless reaching high-quality outcomes.
What’s Subsequent
With GenAI instruments powered by Databricks Mosaic AI, Česká spořitelna staff are actually in a position to acquire entry to solutions present in a variety of paperwork by way of “sensible search” performance. For instance, the buying group might have to seek the advice of a whole bunch of pages of course of documentation on the right way to management and approve funds to completely different nations. Earlier than leveraging Databricks, it might take staff hours to search out the proper info they want. Now, RAG-powered search offers staff solutions inside seconds, together with citations and hyperlinks to the supply doc.
Wanting forward, there are many alternatives to discover extra GenAI workloads at Česká spořitelna. We intention to create a sturdy integration between Databricks and Česká spořitelna’s inner database name middle recordings. This can unlock new use instances resembling churn detection, sentiment evaluation, and gross sales sign detection since Databricks is the go-to platform for streaming knowledge. These every day experiences will enable Česká spořitelna to react to adjustments in actual time whereas reaching value reductions with improved high quality assurance of their name facilities.
This weblog put up was collectively authored by Petra Starmanova (Česká spořitelna), Tereza Mokrenova (DataSentics), Dalibor Karásek (DataSentics) and Joannis Paul Schweres (Databricks).
