Profinit

Since 2005, Profinit has been cooperating in the field of Business Intelligence (BI) with Komer?ní banka (KB) (a member of the Société Générale international financial group), on a continuing basis. The projects we have implemented represent a wide portfolio of consulting services in BI & DWH solution development, but also in terms of infrastructure and operations. Key projects in recent years have been, for example, the migration and development of a management information system, and BI solutions for the bank’s risk management and distribution departments. The volume of services is on the order of several thousand MDs per year, the greater part of the work is contracted as fixed deliveries. Profinit has been a reliable long-term partner for KB in BI. Read More

Project background Our client, Raiffeisenbank CZ, offers an outstanding online service and is continuously pushing out new products to meet customer needs and expectations. The bank was keen to maintain its position in the industry, so we looked at how we could use state-of-the-art technology to help them. Working alongside our client, we asked the question, “How can we use this collected data fully, in a way that enables us to offer bank customers an even better service?” Our answer came via applying advanced data analytics and machine-learning methods to the problem – enabling us to make competitive loan consolidation offers to the right customers. Challenge Detecting loan instalments paid to other lenders, within customer transactional data, involves executing complex computations over hundreds of millions of records on a daily basis. A robust big data pipeline for high parallel data processing is needed, as well as the inclusion of suitable data science tools and methodology. It is cutting-edge work. In fact, this project was the very first implementation of this kind into the bank environment, without any existing technological or architecture blueprint. Solution We designed a complex processing pipeline, implemented on a local Hadoop cluster, including data science tools such as Apache Spark, Hive and Jupyter. In order to identify customers with loans elsewhere, we applied our instalment detection tool. Using an instalment detection tool The tool processes customers’ banking transactions and related data. It’s calibrated specifically to automatically detect loan instalments for each customer. The model is based on advanced statistical and machine-learning methods such as Multi-layer Bayesian Networks. Implementation into the big data pipeline means it can handle processing huge volumes of transactional data – even billions of records on a daily basis. Business needs The solution needed to meet the following specifications: Identify clients with competitor loans for targeted marketing campaigns focused on consolidation More accurate assessment of customers’ credit risk scoring Adding data science tools to bank infrastructure and setting up a big data processing pipeline High-performance technology to promptly process clients’ transactions without delays Tech stack Hadoop Apache Spark Hive Python R Project Summary The solution we designed and implemented has achieved these results for the bank: The new solution can detect twice as many competitor loans as the former one. A new big data pipeline now processes billions of transactions daily. Daily leads for loan consolidation offers and better campaign targeting. Information about new loans elsewhere improves credit risk management of debtors. Read More

We participated in the development of Big Data Management Platform for Telekom Germany. Storing, integrating and analysing large volumes of data using state-of-the-art tools and technologies with the aim to replace selected traditional business intelligence systems. Read More

Project background & challenge Our client, My Community Finance, the UK’s largest provider of consumer loans in the credit union sector, was transforming its cloud IT infrastructure to catch up with rapid business growth. The new microservice architecture was chosen to better match very agile and flexible IT needs. The current deployment setup and infrastructure components were set up for traditional incremental releases unsuitable for continuous deployment. The Profinit DevOps team enhanced the existing infrastructure and recreated a new deployment pipeline. DevOps Solution The first action was to upgrade major infrastructure pieces to the up-to-date versions. Profinit’s primary approach was to create an infrastructure-as-code (IaC) solution automating the whole pipeline as much as possible using Jenkins and Amazon Elastic Kubernetes Service. Documentation on how to use and operate the system was created as a matter of course as well as guidelines for new service developers. The pipeline now enables the deployment of new microservices with one click. Business needs The solution needed to meet the following specifications: Take over existing infrastructure and build a new CI/CD pipeline Modernise automated deployment processes and components Enable deployment of new web applications with one click Tech stack AWS cloud Amazon Elastic Kubernetes Service Jenkins Project Summary The solution we designed and implemented has achieved these results for the company: A microservice architecture was chosen to catch up with rapidly growing business and flexible IT needs We fully automated the deployment pipeline creating an infrastructure-as-code solution The solution now enables the deployment of new microservices with a single click Read More

Project background The UK fintech company My Community Finance, the most prominent lender in the UK credit union sector, was looking for a strategic partner in machine learning and data analytics. The first step to achieving the ultimate optimised underwriting process with a personalised offer was to build a behavioural model to predict the probability of acceptance of each client quote with the given parameters. Profinit accepted a request for proposal (RFP) by My Community Finance in the form of a contest to get the best prediction results from an anonymised dataset. Our data science team successfully tackled the challenge and delivered the best model out of all the competing vendors within two weeks. Challenge The model needs to process hundreds of client features from the underwriting process and external risk to credit-bureau data. Furthermore, the computational time is critical as each offer needs to be shown to the customer within a window of a few seconds when other competing offers are generated through web aggregator comparison services such as Experian. Solution: Machine learning Profinit designed and implemented the model for assessing each individual client quote. The behavioural model enhances the underwriting process by optimising offers for unsecured loan products using machine learning. The end-to-end implementation consists of a real-time data processing pipeline running entirely on the AWS cloud and MLOps environment, enabling failover model retraining with a single click. The solution provides stable, highly accurate predictions (85% AUC) and makes decisions in less than 100 milliseconds. The number of loan offers accepted increased by 30% as a result of using the solution for the individual offer for each customer. Business needs The solution needed to meet the following specifications: Process hundreds of client features from the underwriting process and external risk to credit-bureau data Deliver high-precision predictions for thousands of quotes daily with minimal latency (milliseconds) Enable failover model retraining with a single click Increase the number of loan offers accepted Get valuable insights from quote data Tech stack Python R MLflow AWS Jenkins Flask Project Summary The solution we designed and implemented has achieved these results for the company: We delivered a behavioural model to optimise underwriting with a personalised offer in real-time with minimal latency. The model predicts the probability of acceptance of each client quote based on hundreds of features incl. credit bureau data. The number of loan offers accepted increased by 30% as a result of the individual offer for each customer. Read More

Project Brief Between 2014 and 2023 we delivered a complete solution for one of the largest cryptocurrency exchanges in Central Europe – Coinmate. Project Summary In late 2013, Coinmate approached several large software companies with a request to develop a cryptocurrency exchange, including a trading core. One of these was Profinit, which prepared the design and costing of a software solution for Coinmate as part of the RFP process. Coinmate rated Profinit's solution as the best of all. Profinit's experience in banking environment development was one of the key factors that suited Coinmate, as the goal was to build an exchange in line with banking standards. Implementation of the project was preceded by an analysis and design of a proposed solution which, once it was approved by Coinmate, was followed by the actual development. At the beginning of 2014, Profinit became the exclusive vendor for the development of the Coinmate bitcoin exchange. It was a complex project that was created on a "greenfield" basis and at a time when there was no company with experience in cryptocurrency exchange development on the Czech market. A total of 15 Profinit consultants worked on the project in various roles. Deep knowledge of the development of banking systems as well as enthusiasm for cryptocurrencies proved to be their important strengths. The development of the platform was iterative and after 6 months of development, in October 2014, the new cryptocurrency exchange was deployed into the production environment. One of the biggest challenges of the project was to design and develop a trading kernel that would provide buy and sell order entry and matching. A specific challenge was also to understand the workings of each cryptocurrency and provide integration to their blockchain so that users could make deposits and withdrawals. During 2015 - 2023, Profinit consultants worked with the exchange's internal team on numerous extensions and related integrations, such as client onboarding, trading and marketing. Based on Coinmate's requirements, developers were able to migrate between third-party verification services—such as Bank ID—add new cryptocurrencies and improve the security of funds deposited on the exchange. Tech Stack Java Oracle Spring AWS Jenkins MyBatis The Business Needs The required solution had to meet the following specifications: To analyse, design, develop, test and enable the operation of a cryptocurrency exchange designed primarily for clients in Europe, with banking-systems level security, including AML and KYC procedures. To allow clients from the Czech Republic to make deposits and withdrawals in Czech crowns, which means ensuring integration with banks operating in Czechia. Systematically cover the processes related to trading (order entry, trade settlement, etc.) and ensure that the exchange seamlessly serves both large traders who provide liquidity on the exchange and users with small transactions. Provide integration for third parties and other services (e.g. prepare API for trading robots). Solution The development of the exchange was based on banking standards, i.e. using the Java language and the Oracle database. Profinit’s robust solution can handle tens of thousands of users and can process tens of exchange orders per second. In addition to the actual delivery of the turnkey solution, Profinit implemented software development processes. Testimonial "Profinit's team of experts created a cryptocurrency exchange for us based on our requirements from the ground up. They designed a comprehensive solution, which we successfully implemented, and helped us develop it further. Thanks to their experience in the banking environment, we were assured of the high security of the exchange. We also see Profinit's consultants as important partners who helped us make key decisions to further develop our trading platform." Roman Valihrach, Founder of Coinmate Read More