Qorus-Infosys Finacle Banking Innovation Awards 2024

AI Supported New Generation Internal Demand Management System

Submitted by
10/06/2024 Banking Innovation


The project is an R&D Project developed on the Vakıf Katılım Demand Management System and includes the development of an NLP and classification model to be used in internal banking processes.

Innovation presentation

Demand management systems are critical in the banking sector, both in terms of customer-bank relations and in-house bank activities. In the banking sector, where legislation and regulations are very strict, activities must be carried out without errors. According to the banking law, activities are subject to multi-stage and complex evaluation processes. In this context, methods such as free-format text correspondence, e-mail correspondence, telephone, etc. are quite common in customer and internal communication. As a result;

• The need for manual effort increases for the processes to proceed smoothly.

• Since the demands and complaints sent through the demand management system concern different processes, the problem cannot be solved at once.

• Whenever complex demands sent through the demand management system cannot be solved through the "helpdesk" system, they are resolved outside the system by phone, e-mail, etc. channels. In this case, the possibility of tracking the data to improve the process is eliminated. Every demand management system that does not function properly increases operational risk as it is open to errors that may cause financial loss for the bank.

• As a result of the demand management system that cannot be optimized, the need for extra effort arises and causes inefficient use of resources.

Vakıf Katılım uses the Atlassian Jira Request Management system to track work between internal teams. Through this system, users can open requests for their problems/requests and track many pieces of information such as the path the opened request took until it was resolved, comments, and information about the teams/units it went to from the moment the record was first opened until it was resolved. These requests opened by users are not always opened in the correct category, and it takes time for the request to reach the relevant unit, which delays the solution of the request. Failure to open requests to the appropriate unit leads to loss of performance and efficiency.

The developed model, it is aimed to eliminate the problems encountered in workflow processes and increase efficiency by developing a language understanding model using the records of requests (demand management system) kept within Vakıf Katılım and frequently used in operational processes.

As a result of the developments, a model with 75% accuracy was developed and improvement work on the model is ongoing. At the end of the project, it is aimed to transform the model results into reports that will produce value. The developed model aims to shorten the response times of the requests in the demand management system, reduce operational loads, and increase internal customer satisfaction. It is planned to use the developed model in other internal banking processes.

Uniqueness of the project

Today, demand management systems have become a basic requirement used in many areas, not just banking. Here, solution times are a parameter that every sector strives to improve. Improvements to be made in demand management systems are provided by customizations in the demand management system. Many companies in the banking sector use customized language models in various processes. These language models are used in many areas such as customer service, customer relationship management, risk assessment, and fraud detection. The purpose of these banks in developing and using their language models is similar and is to help understand customer demands and questions, explain the bank's services better, and solve customer problems.

Participation banking operates without interest based on Islamic finance principles and uses methods such as profit-loss sharing; traditional banking operates on an interest basis and loans are provided with interest income and interest is paid to deposit accounts. Participation banking differs from traditional banking in many ways. Therefore, the development of a language model specific to participation banking is a very important point. Although there are language models used by many companies, a language model specific to participation banking was first developed with the project. With this model developed within Vakıf Katılım, a solution is being developed that will eliminate the problems encountered in branch operation processes and access to the most appropriate source. This language model aims to eliminate the problems encountered in workflow processes and increase efficiency. The developed model will ensure that the requests opened by users are opened in appropriate categories, the request reaches the relevant unit directly, and this will ensure that the request is resolved in the shortest time.

Want to keep reading?

Become a Qorus member to get access to all our innovations

Interested in learning more? Speak to Boris, Qorus's Content Lead

Qorus has a library of almost 8,000 innovation case studies across critical areas like customer experience, sustainability, marketing & distribution and more that can be used to inform your decision-making.
Contact us

Related innovations

14/06/2024 Banking Innovation

Reclaiming our Relevance

Kootenay Savings Credit Union (KSCU) has undertaken a comprehensive new branding initiative that reflects both the values of the credit...

13/06/2024 Banking Innovation

Finacle Enterprise Event Manager

Specialize in solving pain points., Identified delay in notifications and real-time data transmission between core and satellite systems. We along...

13/06/2024 Banking Innovation

Self Service Sales for Fostering Growth

Every month 5 million calls enter IVR at Yapı Kredi Customer Relations Center. Not only providing self service transactions, we...

13/06/2024 Banking Innovation

Analytics For Revenue Generation: Speech Analytics for Sales Growth

Using Speech Analytics, we have successfully crafted a sales strategy focusing on data gathered from customer calls. Successfully, we created...

Related news & insights

Digital Reinvention
14/06/2024 Interview

NewTech Friday: Vespia – Helping businesses stay compliant with regulations

Julia Ront, Founder and CEO of Vespia, tells Qorus’ Boris Plantier about the story behind her pioneering AI business verification...

Digital Reinvention
11/06/2024 Article

Banking Innovation of the Month: Intesa Sanpaolo’s smart knowledge base through GenAI digital advisor

This month’s Qorus-Infosys Banking Innovation Award goes to Intesa Sanpaolo for their Smart Knowledge Base powered by generative AI. This...

Digital Reinvention
11/06/2024 News

Revolut introduces Wealth Protection for summer travel season

Revolut, a leading global fintech, is launching Wealth Protection, a new feature aimed at safeguarding customer savings from pickpockets and...

Digital Reinvention
10/06/2024 Article

Qorus Innovation Radars: Showcasing the best of the innovation awards

These in-depth pieces showcase the winning innovations from our competitions, featuring both written content and videos.