Use Cases

Chatbot Enhancement: A Success Story with Türkiye İş Bankası & Maxi

Overview

This project involves a study conducted by Co-one for Türkiye İş Bank's chatbot, Maxi, focusing on text annotation and intent classification. Co-one collaborated with Türkiye İş Bank to enhance the performance and accuracy of Maxi, the bank's AI-powered chatbot, in understanding and responding to customer queries. Through comprehensive text annotation and intent classification, Co-one aimed to optimize Maxi's natural language processing capabilities, ensuring a seamless customer experience and efficient query resolution.

The Problem

Before the project, Türkiye İş Bank's chatbot, Maxi, faced challenges in accurately understanding and classifying customer intents. The existing system lacked the precision required to correctly interpret and respond to a wide range of customer queries. This led to inefficiencies in providing timely and accurate information.

Customer's Data Labeling History

As a solution to the data labeling need for the company's Chatbot project, they tried to annotate data in-house. However, since a data labeling team has not been established and data labeling is not the main job of the employees, this process proved costly and time-consuming.

Customer's Meeting & Agreement Process with Co-one

Co-one caught the attention of the customer in an acceleration program, Workup. After a successful demo in December 2021, an agreement was reached in April 2022 to deliver text classification data with a monthly volume of 200,000 under an annual SaaS model.

The Data Labeling Process and the Power of The Crowdsource

Co-one's Crowdsource Team annotates data based on industry expertise and accuracy scores. To ensure accuracy, each data point undergoes manual labeling by three annotators. This effectively solves edge cases, such as distinguishing between generic needs and specific banking errors.

Cross Validation

AI Cross-Validates the data to detect mismatches, which are then corrected by the Co-one Quality Team. This ensures unbiased text labeling and high-quality data control through the power of crowdsourcing.

Data Security

Co-one ensures data security through authorized access methods and preventive protocols. All data processed is only accessible via authenticated clients with expiring access tokens, complying with HTTPS and Google authentication systems.

Customer Review

"Co-one's intent generation service for our chatbot, Maxi, has accelerated our data feeding process by analyzing Maxi chatbot dialogs on a weekly basis. Maxi's dialog accuracy rate has reached up to 98% with the valuable contributions of Co-one."

— Gamze Ortakaya - Innovation and Digital Strategy Sub Manager

References

More in use cases

MANK and Co-one case study cover on evaluating a banking voice assistant.

Use Cases ·

How MANK evaluated its banking voice assistant

MANK worked with Co-one to automate call-flow testing, assess how its voice assistant handled adversarial conversations, and improve speech recognition and synthesized speech.

Talk to Co-one

Bring a workflow. We’ll start there.

Show us where your agent makes decisions or takes action. We’ll discuss what to simulate, what to validate, and where runtime controls belong.

Book a demo

Choose whether to allow optional analytics and marketing tags.