Banking – CALIGO

Asset-Liability Risk Management

Caligo — Wed, 23 Nov 2022 11:11:07 +0000

Asset-Liability Risk Management (ALM)

Business Situation

Asset-Liability Risk Management (ALM) covers the entire process of managing the risks on the Asset and Liability items of the Bank’s balance sheet in a way that maximizes their profits. The automation of the ALM process ensures that all work to be done in this multi-component process can be done with minimum error, minimum effort and maximum efficiency. In this context, all main topics such as determining the product structures and scope of the Bank’s portfolios, making cash flow-based analyzes and forecasts based on maturity, automation of simulations and scenario analyzes, and transforming the outputs of all analysis processes into strategies and reporting constitute the basis of ALM Automation.

Our Approach & Solution

During the project, the biggest contribution was to work proactively and keep in a close contact with stakeholders. We followed the progress by holding weekly meetings and discussed all issues in a transparent way. The proper and efficient preparation of the data model and integration flows has been one of our main tasks in the project. In order to deliver the project on time and smoothly, regular checks were made and alarm mechanisms were designed. Having well documented processes and data flows, understanding the languages of business units has always been one of our main success criteria.

Technologies

Stored procedures -using Microsoft SQL Server Management Studio– for data integration and feeding data model
ETL tool (Informatica) and Databases procedures for data integration and feeding data model

Churn Datamart

Caligo — Wed, 23 Nov 2022 10:53:16 +0000

Churn Datamart

Business Situation

The client wanted to design a data model that could be used to analyze the behavior of the current customers of the bank, to identify customers who may give up using the bank’s products by preferring another bank and to decide on the actions to be taken to retain the customer in a timely manner. The concept of Churn Analytics has become a very important issue for the sector, where the competition is at a high level and in terms of satisfying the existing customer and establishing long-term customer relations rather than aiming to gain new customers.

Our Approach & Solution

During the project, working collaboratively with project team was crucial. We understood the variables in the Churn Data Model on SAS and determined the needs accordingly. In this way, we created datamarts that feed the Churn Data Model. We worked with agile project management and closely followed the progress through daily diaries and weekly status meetings. In this way, the requested variables were delivered without errors in accordance with the planned schedule.

Technologies

Dynamic stored procedures using Microsoft SQL Server Management Studio for data integration and feeding data model.

Risk Models Validation

Caligo — Tue, 17 May 2022 10:36:03 +0000

Risk Models Validation

Business Situation

In the banking industry, credit risk models have to comply to high standards in order to be compatible with banking regulations. Additionally, they have to satisfy model performance thresholds set by organizations themselves during periodical monitoring processes. To satisfy performance and regulative requirements, financial institutions have to perform validation studies. Cutting edge technologies and new algorithms opened a new era for data analytics in banking. Due to the potential of increasing model performance, the interest in AI models increased rapidly in the last decade. With this purpose our client wanted to apply a validation framework to self-learning AI Based models.

Our Approach & Solution

Our approach is to apply the validation framework to readily developed AI models. On top of validating currently performing model codes, we are challenging their code structure as well.

Technologies

We implemented our validation controls via PyCharm or Spyder based on Python language.

PD Model Development

Caligo — Tue, 17 May 2022 10:17:47 +0000

PD Model Development

Business Situation

Credit risk assessment models are used in the finance industry to create a balance between the ratio of non-performing loans (NPL) and the approval ratio. Our client wanted to renew all credit risk assessment models to decrease their NPL Rates and increase their profitability. With this purpose, they wanted to include behavioral components into their models and integrate various scoring modules as a unique score.

Our Approach & Solution

Creating an effective credit risk model requires building enriched features by combining statistical methods with domain expertise and get the best out of it. In the light of this knowledge, we have first developed a new set of variables and then used modelling techniques to increase the model performance of the existing models. With the implementation of our solution, our client will be able to differentiate more effectively between non-performing and performing customers and manage provisions and capital calculations effectively.

Technologies

We implemented our model pipeline via SAS Enterprise Miner and SAS Enterprise Guide.

Customer Behavior Analytics

Caligo — Fri, 09 Oct 2020 20:57:18 +0000

Customer Behavior Analytics

Business Situation

Customer behavior analytics helps organizations to make data-driven decisions at individual customer level. Companies can utilize their customers’ internal (payment, purchasing, transactions, etc.) and external (digital, location, etc.) to learn about what customers want and what they are willing to do for future. So, they can create a better customer experience, increase royalty and increase their profitability.

Our Approach & Solution

We can gather structured and unstructured data, use data science tools to process them and apply most appropriate machine learning models for customer behavior analytics tasks like customer segmentation, retention, royalty and marketing analytics.

Technologies

Any analytical tool can be adopted for model development and developed model can be implemented on your current customer analytics tools, or we can offer integrated environments for your end-to-end process.

Stress Testing Models

Caligo — Fri, 09 Oct 2020 20:55:29 +0000

Stress Testing Models

Business Situation

Stress testing is required to test the resilience of banks to different plausible shocks. Stress tests are analyses conducted for hypothetical macroeconomic and financial scenarios to determine whether a bank has enough economic capital or provisions to stand economic crisis. Federal or International authorities like BDDK, IFRS and EBA requires all banks of a size to conduct stress tests and report results regularly.

Our Approach & Solution

Considering the authorities’ guidelines and minimum requirements we develop multiple econometric models and compare forecasting performances to select the best model. And we design the internal and external reports for stress testing results.

Technologies

A proper econometric model development tool and a report design tool are main technological requirement of a well – designed and automatic Stress Testing framework.

Early Warning System Models

Caligo — Fri, 09 Oct 2020 20:52:36 +0000

Early Warning System Models

Business Situation

Early warning models are one of the main pillars of monitoring systems of Financial Institutions. This system models aims to identify very early bad indicators before a credit starts to shows payment disability. There are alternative frameworks for EWS models and Banks can define the most proper framework based on their supervisory obligations, bank risk assessment systems and chosen modelling methodology.

Our Approach & Solution

We can develop end-to-end EWS system for a Bank including hands-on modelling, defining statistical rule sets and system integration/a new system design. We develop multiple methodologies for modelling and chose the best with business expectations and find the most optimal system solution.

Technologies

We adopt a technology flex solution and can develop models and system on your existing technology solutions.

IRB Compliant Risk Parameters

Caligo — Fri, 09 Oct 2020 20:49:55 +0000

IRB Compliant Risk Parameters

Business Situation

Banks are allowed to calculate their own risk parameter estimates for regulatory capital calculation under Basel II. This is known as internal ratings-based approach for credit risk parameters. For this approaches a bank should take two major steps:

Exposure categorization (according to Basel II definitions)
Estimate risk parameters, probability of default (PD), loss given default (LGD), exposure at default (EAD), maturity (M) as inputs to risk weight functions

Our approach & Solution

As CALIGO we provide tailor-made model development and validation projects for all risk parameters both in hand-on development and methodological advisory. We start with the current situation analysis, define the development points and build modelling structure on top of these analyses.

Technologies

There are two parts of technological requirements for risk parameters:

Model Development: Our models can be developed on R, Python, SAS or KNIME
Model Implementation: Developed models can be implemented on your current risk solutions

SME Segmentation

Caligo — Fri, 09 Oct 2020 20:47:33 +0000

SME Segmentation

Business Situation

In order for banks to provide the advantages provided to SMEs, they must classify companies that meet the conditions specified by the relevant ministry as SMEs. One of the most important expectations of the project is that the variables and rules can be changed easily, as the ministry could change the rules periodically.

Our approach & Solution

Although it seems easy to apply the specified conditions at the beginning of the project, the quality of the input data and the provision of financial balance sheet data can be considered as the most critical issue. Our approach in the project was to provide prototype and statistical data to enable the relevant business lines to make easy decisions while determining the rules. Completing the missing information of thousands of customers by providing detailed analysis data and compliance with SME definitions has been one of the most important outputs of the project.

Technologies

We implemented our processes via Oracle Databases and Oracle Data Integrator.
This output exported as flat files and transferred through FTP or e-mail notification.

Fees & Commissions Integration

Caligo — Fri, 09 Oct 2020 20:39:39 +0000

Fees & Commissions Integration

Business Situation

Central Bank of the Republic of Turkey had requested periodic reporting which includes fees and commissions of all products from banks to ensure transparency and audit. Due to the different operation of the fee and commission modules on a product basis, it could be called the most important challenge for the separation and classification of transactions in a short time. Due to the variety of products in banks, it was necessary to work with different departments to carry out analysis, development and testing processes in parallel.

Our approach & Solution

Within the scope of the project, a process with very high sensitivity and requiring strict follow-up and project management has been implemented since it is the counterparty regulatory authority and has a certain time constraint. As a solution, by dividing the process into manageable parts, data consistent with accounting is produced and applied over production data with relevant departments.

Technologies

We implemented our processes via Oracle Databases and Oracle Data Integrator.
This output exported as flat files and transferred through FTP or e-mail. notification.