Мы используем файлы cookie для быстрой и удобной работы сайта. Выберите, какие файлы cookie вы разрешаете нам использовать. Подробнее в Политике конфиденциальности.
We use cookies to ensure our website works quickly and easily. Choose which cookies you allow us to use. Learn more in our Privacy Policy.
Discuss the project
Send a request and our specialists will contact you within 1 hour.
By clicking the "Send" button, you give your unambiguous consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Get development
Submit a request and gain access to a training manual from a leading company expert!
By clicking the "Send" button, you give your unambiguous consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Deploying a Data and ML platform
for a major payment service provider in Uzbekistan
for a major payment service provider in Uzbekistan
20%
30%
TTM Data Readiness Acceleration Client 360
Accelerating TTD for testing new product hypotheses by using a single, described data model.
Customer
The largest payment company in the Uzbek market
Solution
A data platform was developed and deployed
based on S3 Ozone, Airflow, Spark, and Iceberg;
A hybrid data model, Client 360, was designed and implemented
using the Data Vault 2.0 methodology;
An ML platform based on ClearML, Kserve, and Feast was installed, and ML credit scoring models were launched using the platform.
based on S3 Ozone, Airflow, Spark, and Iceberg;
A hybrid data model, Client 360, was designed and implemented
using the Data Vault 2.0 methodology;
An ML platform based on ClearML, Kserve, and Feast was installed, and ML credit scoring models were launched using the platform.
Design and development of a Client 360 data model based on the new Data Lakehouse architecture;
Design and implementation of an ML platform based on ML credit scoring models.
Design and implementation of an ML platform based on ML credit scoring models.
Task
Business values
Reducing operational risks
Up to 40% less ML service downtime and incidents thanks to monitoring, alerts, and automatic model rollbacks.
Saving
Infrastructure and operational savings → 20–30% of hardware and cloud costs thanks to centralized servicing (KServe), autoscaling, and monitoring.
Saving on specialists and abandoning the “home-made” platform → 30–50% of the platform team’s payroll.
Economic effect: +10–30 million ₽ additional profit from each case due to an earlier launch.
Potential impact: up to 30–40 million rubles/year in salary savings (DevOps + MLOps).
Speed
Accelerating the time to maturity of Client 360 data by 20%.
Accelerating the time to maturity for testing new product hypotheses by 30% through the use of a unified, defined data model.
Increasing the availability and quality of Client 360 data;
Reducing the time to maturity of new ML cases (scoring, anti-fraud, next best offer) → 2-3 times faster: from 3-6 months to 4-8 weeks.
Accelerating the time to maturity for testing new product hypotheses by 30% through the use of a unified, defined data model.
Increasing the availability and quality of Client 360 data;
Reducing the time to maturity of new ML cases (scoring, anti-fraud, next best offer) → 2-3 times faster: from 3-6 months to 4-8 weeks.
By clicking the "Submit" button, you expressly consent to the processing of your personal data to the extent and for the purposes defined in the Personal Data Processing Policy.
Development of software
and Big Data solutions
and Big Data solutions
Send a request and our specialists will contact you within 1 hour
You can attach three files up to 3 MB each. Formats: doc, docx, pdf, ppt, pptx
Choose a convenient method of communication
Сообщение об успешной отправке!