Ivan Zhukov

A fintech software company building products for banks, consumer lenders and financial marketplaces.

I joined as a data analyst in June 2024 and have led the five-person analytics team since February 2025. We work on offer ranking, scoring, external-data enrichment and applied machine learning. I help set the direction, work through the analytical approach with the team, and coordinate delivery with engineers and the people using our products.

One of my main projects is TakeUp, which decides which lender offers a visitor sees on a financial marketplace and in what order. I led its analytical design and development, replacing manually configured placements with ranking based on commercial performance, credit-risk signals and actual customer outcomes. TakeUp improved revenue by 11.1% against the previous ranking logic on comparable traffic. Across its wider deployment, estimated additional revenue has averaged around £75,000 a month. It is now a core part of the company’s WebEngine platform.

Another project asks a simple question: when is a message worth sending? I designed and validated a machine-learning model to avoid low-value communications, then coordinated its rollout. Across all business users, it saves around £36,000 a month, or about 2% of communication costs, without materially reducing valuable customer traffic.

The team’s work also includes detecting bot visits, evaluating external scoring models, and developing the Enrichment Service. A recurring part of my work is deciding whether a new signal or model adds enough value to justify its cost, then helping turn that finding into product logic.

A B2B fintech company building scoring, data-enrichment and lead-generation products for financial services.

At oneFactor, I worked on turning external data into useful signals for banks, lenders and insurers. A major part of this was a reusable Spark component that converted pseudonymised communication events into behavioural features for scoring, customer segmentation and lead generation.

I led the product and analytical side: deciding which events mattered, how to classify them, what time windows and thresholds to use, and what the output should look like. I worked with data engineers to put that logic into production and scale it. This enabled 45 new production pipelines and made the feature logic reusable across client projects.

I also carried out more than 30 client pilots and validation studies. These covered questions such as whether we could match enough customers, whether a score added useful information, and whether the economics worked in practice. I presented the findings to client and commercial teams to help decide what to launch or change. I also developed 16 communication scenarios, contributing to an approximately 3% improvement in conversion.

This work supported the expansion of the lead-generation business, whose client base grew from 13 to 30 organisations and annual revenue from about £6.5 million to £10 million.

One of the top 10 largest banks in Russia

Identified and helped fix a critical error in the credit decisioning system within the CRM integration, restoring services for 110,000 clients and contributing to an approximate financial recovery of £2.3 million over six months.

Developed and tested guidance for the PACL credit decisioning process, expediting client approvals and offers. This collaboration with IT and technology teams accelerated analysis and client batch approvals.

Devised a revenue calculation method based on peak debt load, reducing gross loss risk by 0.4% for clients with low credit scores, considering full and partial loan repayments to enhance risk management strategies.

Conducted comprehensive research on internal fraud within bank offices, uncovering six suspicious activities and prompting internal audits, leading to strengthened internal control mechanisms and security.

Mentored a group of Data Analyst interns, training them in SQL, risk analysis, and core business processes.

A leading Russian insurance company specialising in auto, real estate, and health insurance

Automated call centre list preparation with SQL scripts, reducing prep time from 1.5 weeks to 4 days.

Developed four SSRS reports for the Digital Insurance division, including sales funnel diagrams, streamlining data reporting.

One of the top 10 banks in Russia and a pioneer in innovative technological solutions to the Russian financial sector

Delivered an automated ROI calculator for individual CIB clients and segments, utilising a prefab methodology to implement the script in SQL, leading to streamlined calculations and portfolio assessments.

Managed workload assessments for CIB Salesforce managers in collaboration with the HR CIB department, constructing an SSRS report with daily updates and recommendations to optimise workforce efficiency.