Artificial Intelligence System for crediting manufacturer/importer of goods
Relevance
Banks are currently implementing artificial intelligence (AI) and machine learning into every business process and plan to extend this technology to all areas of their business. For example, banks have long carried out the primary scoring of borrowers automatically. The introduction of AI systems ensures the processing of documents necessary for the formation of a client dossier. Integrated recognition technologies allow you to automatically process and enter customer data when opening accounts and performing banking operations where identity verification is required. AI technology is used in the following main areas: risk management, small and medium-sized businesses and retail. In risk management, AI helps prevent fraud, in small and medium-sized businesses, as well as in retail, with the help of artificial intelligence, the bank solves the problem of increasing sales conversion by modeling customer preferences and using forecasting systems. AI technology could also be massively used by large banks for lending to medium and large enterprises. Artificial intelligence is used to solve a wide variety of tasks, and one of them is to reduce the average customer service time, increase the share of solving their requests at the FCR stage (First Call Resolution, first call resolution ratio) due to high-quality and convenient service achieved through automation call center operations. The proposed intelligent system is based on machine learning models that are widely used in various fields of human activity and continue to prove their effectiveness and practicality in real-life tasks. However, in the financial sector, in particular in the tasks of the bank, there is a need for in-depth study and implementation of AI technology to improve work efficiency. In Kazakhstan, there are no credit lines for manufacturers and importers of goods, so many companies use foreign solutions to commercialize technologies in the domestic market. Consequently, confidential user data exported using foreign solutions adversely affects the economy of Kazakhstan. These include the dissemination of personal data, which is now valued as a valuable national resource.
Purpose
The goal of the project is to create an intellectual system based on a scoring model. The scoring model will allow banks to quickly make decisions on customer lending based on big data and artificial intelligence methods.
Expected and achieved results
As a result of the project, at least 3 (three) articles and (or) reviews will be published in peer-reviewed scientific journals, indexed in the Science Citation Index Expanded of the Web of Science database and (or) having a CiteScore percentile in the Scopus database of at least 50 (fifty) ;
- as well as at least 1 (one) article or review in a peer-reviewed foreign or domestic publication recommended by Committee for Quality Assurance in the Sphere of Education of the Ministry of Education of the Republic of Kazakhstan;
1. Scientific effect:
The results of the project are of great scientific importance for the development of financial technologies. The resulting intelligent system will allow the use of tools to solve a new range of problems using machine learning algorithms and artificial intelligence. The developed methods will help to process financial documents, create classifications, use and compare various machine learning algorithms on non-standard tasks.
2. Socio-economic effect:
The developed intelligent system will automate all lending processes, which will speed up the decision-making time, responding to borrowers in an interactive form. In addition, a tool will be created that will allow banks to process unstructured data on producers and importers of goods and use it for their own purposes. An intelligent system for processing big data in the financial sector will appear in Kazakhstan, which is very important for diversifying the Kazakh market during the economic crisis.
3. Commercialization of the obtained scientific results:
Experimental analysis, testing and implementation of the developed intellectual system in second-tier banks is planned for 2024-2025. The results of the project can be commercialized.
4. Target consumers:
- Small and medium businesses;
- second-tier banks providing financial services in the Republic of Kazakhstan on the world market.
5. The developed model will serve the development of departmental software and hardware systems.
6. The results of the work will be presented to all interested business areas, the public sector and public organizations, as well as the scientific community and the public. Participation in annual scientific conferences organized by the Ministry of Education and Science of the Republic of Kazakhstan and at the international level is expected.
7. Target consumers of the results obtained: Small and medium-sized businesses, financial institutions of the Republic of Kazakhstan, etc.
8. Opportunities for breakthrough results containing risks; impact on the development of science and technology: Since the created intellectual system with developed services for processing data on manufacturers and importers of goods can be quickly adapted to most other types of business, breakthrough results are possible. The general formalized approach to work developed by us and the data collected give high results when applying the artificial intelligence system to large businesses.
9. Dissemination of the results of the work among users, the scientific community and the general public:
The intelligent system can be distributed to businesses, industries and government agencies serving a wide range of economies. The obtained scientific and practical results may have an impact on the development of financial technologies and information technologies.
Research team members with their identifiers (Scopus Author ID, Researcher ID, ORCID, if available) and links to relevant profiles
Hirsch index: 4
ResearcherID: E-4387-2016
ORCID: 0000-0002-1596-561X
Scopus Author ID: 57160071400
2. Сатыбалдиева Рысхан Жакановна, Кандидат технических наук, Индекс Хирша: 2 Researcher ID: DZS-7641-2022 ORCID: 0000-0002-0678-7583
Scopus Author ID: 55387664200
3. Ускенбаева Раиса Кабиевна, Доктор технических наук, профессор, Индекс Хирша: 8
Researcher ID: ABC-7469-2021
ORCID: 0000-0002-8499-2101
Scopus Author ID: 55623134100
4. Кальпеева Жылдыз Бейшеналиевна, PhD in Computer Sciences, Доктор PhD, Индекс Хирша: 4
Researcher ID: AAG-7613-2019
ORCID: 0000-0002-4970-3095
Scopus Author ID: 56021560300
5. Касымова Айжан Бахытжановна, Phd, PhD, Индекс Хирша: 4
Researcher ID: AAR-5711-2020
ORCID: 0000-0003-2999-5745
Scopus Author ID: 56465965900
6. Акылбеков Олжас Наурызбаевич, Бакалавр, Мастер
Researcher ID: B-7073-2017
ORCID: 0000-0002-7188-5550