Go to main section
Credit decisions based on machine learning
10 min read

Credit decisions based on machine learning

Long waiting for a credit decision is a pain, which is indicated by a large proportion of bank customers.

Credit decisions based on machine learning
Lorem ipsum

Long waiting    for a    credit    decision is a pain, which is indicated by a large proportion of bank customers.    The formulation of an    application,    assessment of    creditworthiness, collateral,    risks, analysis, opinion    and    acceptance are the process steps necessary for granting a credit from the bank’s point of view.      The decision-making process may look a    bit different if the borrower is a client serviced by a financial    institution for a long time.    In such cases, the    lender has a great deal of knowledge about the history of cooperation – it is    possible not only to speed    up    the process of application verification, but even to prepare a credit offer without an application from    the    client.    The article presents the implementation of the module     supporting    the generation of    individual credit    offers using    Machine Learning.

 Whiteaster’s task was to prepare the automation of the creditworthiness assessment of a financial company’s client. The company’s clients are merchants who sell through one of the world’s largest Internet sales platforms, Amazon.    The credit offer was to    be based on creditworthiness and risk analysis. It    assumes that the credit should be possible to be repaid thanks to the sales results on Amazon.     These loans    are a    new product – the company did not have data on the history    of their    granting and repayment.

 The task is divided into several steps:

  •   Collection and assessment of the completeness, reliability and usefulness of available data 
  •   Data analysis,    initial    classification of customers
  •   Preparation of the analytical model,    tests    and verification of results
  •   Building a solution based on Machine Learning modules
  •   Testing, tuning
  •   Implementation in an integrated customer IT environment

 Since in the first stage the offer is addressed to current customers (using other financial products), the company has    a large    amount of data. They are divided into two main groups:

  •   historical data 
  •   current data

 The historical data relate to sales, customer service quality    and    status    on the    Amazon platform.    The available sets of information, apart from the fact that they differ in substance, cover different time periods (from two to six months).

 The second set is current    data describing the activity of the Amazon salesmen    –    current status information, information on sales, products offered, financial and accounting data, information on    loans granted    (currently repaid),    etc.

 Analysis of    available    information    and development of a decision-making model is a    key    element of the project.    In practice   , it is a continuous task    performed all the time during the project implementation. Obtained    indirect results   , conclusions,    diagnosed    special cases, revealed in the course of work and growing knowledge in the team result in the evolution of models, methods    and the list    of data sets in the project. As a result, they lead to system improvement. The methods of data classification are used intensively,    which facilitate the discovery of regularities and relationships.    The knowledge and experience of the client’s specialists cannot be overestimated. Good cooperation, jointly developed solutions    and    ongoing       evaluation of results allow for quick progress. 

 The analytical model    was    based on the conclusions from the analysis of data and its impact on credit decisions. The final loan offer results from many    factors, both of historical and current nature.    One may risk a statement that the observed increase in their quantity is a good illustration of the maturation of decision-making systems.    The architecture of the solution is also affected by the method of data acquisition, the frequency of its updating and the    substantive meaning –    the way    it    affects the final recommendation. As the    results    of the analysis    change – they evolve during the project, similarly, changes in the model follow. As a result of the project, a solution consisting of seven    Machine    Learning models and a calculation module based on designed algorithms was created.

 The decision-making system generates a ranking (Scoring beha w ioralny , corresponding to the degree of credit risk) and a loan amount proposal for each client. It also provides a range of supporting information to facilitate verification but also a justification for the decision. The architecture consists of seven Machine Learning modules in total – five of them analyse historical data. Different models available in the O.ai package are used. Additionally, a number of rules and algorithms constituting the calculation module have been implemented. Teaching ML modules and improving algorithms is a time-consuming process. It requires many tests, changes, repetitions, result analyses, special case diagnoses, etc. The solution accepted for production use – based on its recommendations of credit decisions – was created in less than 1.5 months. Integration with the client’s integrated system took another month. 

    The project implementation required the knowledge of the information model, data model and business model of the Client’s company (not only in relation to the product that was the subject of the works). Good cooperation and highly evaluated results made it possible to define further goals and continue the cooperation.

Latest posts

Innovator of Silesia 2020

Whiteaster received a distinction in the Innovator of Silesia 2020 competition

Are Polish cities equal to smart Vienna?

Vienna is considered to be the most intelligent city in the world. The high standard of living in Austria's smart city is primarily the result of efficient management.

PROsystem. Application supporting the implementation of projects and publication of information.

The projects implemented by the City are a subject of keen interest to a wide range of residents. Investments and renovations are the basic elements of urban infrastructure development.

Analysis of good data quality The success of any business

The data can boldly be described as 21st century oil. We call data a huge, often chaotic collection of information with invaluable business value.

Legal basis for implementation of the Open Data Portal

The construction of Open Data Portals is part of your strategy and supports the implementation of objectives related to and resulting from legal regulations and the programme of extending access to public data.

The best applications created with open data

We repeatedly say how valuable access to open data is for economic development. Thanks to public data made available in an open form, entrepreneurs introduce a number of revolutionary solutions to the market.

The brain-computer interface – what is it and what potential does it have for business?

Mind control has always been one of humanity's key dreams. Devices enabling communication and control by means of human thoughts no longer belong only to the world of science fiction, but to the current reality, which has enormous business potential.
APA Group
Urban Lab
UM Krakow
UM Jaworzno
UM Rzeszów
Strefa Energii
ZOO Chorzów

Copyrights © 2024 Whiteaster

crafted by: mastafu design