Czech financial savings financial institution Česká spořitelna, a division of Austria’s Erste Group, not too long ago collaborated with AI resolution builder DataSentics to discover using GenAI in name facilities. Česká needed to enhance high quality management and optimize prices of their inbound name heart operations, which obtain round 2 million calls per yr. They selected the Databricks Knowledge Intelligence Platform to experiment with each inside and exterior AI fashions to evaluate the effectiveness of name heart brokers.
Exploring a High quality Management System for Buyer Help
The decision heart group at Česká spořitelna needed to check a top quality management system powered by GenAI that may be certain that brokers adhere to scripted tips throughout buyer interactions. A important problem for Ceska was making certain constant agent communication for routine buyer inquiries. When prospects name about account balances, brokers must direct them to on-line banking options, a key enterprise requirement that drives digital adoption and operational effectivity. The assist group wanted a scalable method to confirm agent compliance and preserve communication requirements throughout hundreds of buyer interactions. To attain this, the group started by utilizing Whisper, a speech-to-text mannequin from OpenAI, to transcribe conversations precisely. The problem was to provide human-readable textual content that precisely represented spoken phrases utilized by name heart brokers with out distorting their that 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 inside GPT fashions and open supply fashions equivalent to 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 equivalent to “Did the agent redirect the client to on-line banking?”. The aim of this train was to evaluate how properly these fashions may mimic human understanding and decision-making when verifying compliance with established tips. By evaluating the efficiency of each the interior GPT mannequin and the open supply fashions, the group aimed to seek out the simplest resolution for bettering customer support by automated AI-driven high quality management.
Advantages of the Databricks Knowledge Intelligence Platform for GenAI
The DataSentics group evaluated a number of choices for this resolution, and in the end selected to deploy the Databricks Knowledge Intelligence Platform and Mosaic AI instruments at Česká spořitelna for a number of causes:
- Knowledge Administration and Governance Advantages: Unity Catalog makes knowledge simply accessible for various fashions whereas maintaining delicate knowledge beneath restricted entry.
- Complete Knowledge Processing Capabilities: the Databricks Platform helps your entire workflow of preprocessing of name heart knowledge, from transcription to high quality management. This allows us to provide intermediate outcomes that may be leveraged for different fashions and initiatives, equivalent to advertising, threat evaluation, regulatory compliance, and fraud detection.
- Mannequin Coaching and Help: Databricks supplies sturdy assist 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 simple 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 undertaking, we experimented with varied segmentation methods and gathered a number of precious insights:
- High quality of Enter Knowledge is Essential: The standard of the audio recordings various from consumer to consumer, with some talking quietly or from a distance, which may later have an effect on the accuracy of the transcription. Whisper or related techniques can assist remedy 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 know 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 trying to optimize prices whereas nonetheless attaining high-quality outcomes.
What’s Subsequent
With GenAI instruments powered by Databricks Mosaic AI, Česká spořitelna workers at the moment are in a position to achieve entry to solutions present in a spread of paperwork through “good search” performance. For instance, the buying group could must seek the advice of tons of of pages of course of documentation on easy methods to management and approve funds to totally different nations. Earlier than leveraging Databricks, it might take workers hours to seek out the right data they want. Now, RAG-powered search offers workers solutions inside seconds, together with citations and hyperlinks to the supply doc.
Trying forward, there are many alternatives to discover extra GenAI workloads at Česká spořitelna. We goal to create a sturdy integration between Databricks and Česká spořitelna’s inside database name heart recordings. This may unlock new use instances equivalent to churn detection, sentiment evaluation, and gross sales sign detection since Databricks is the go-to platform for streaming knowledge. These every day studies will permit Česká spořitelna to react to modifications in actual time whereas attaining price reductions with improved high quality assurance of their name facilities.
This weblog publish was collectively authored by Petra Starmanova (Česká spořitelna), Tereza Mokrenova (DataSentics), Dalibor Karásek (DataSentics) and Joannis Paul Schweres (Databricks).
