Senior Risk Analyst - FinTech

- Risk management: participation in activities affecting risk level and LTV, regular review, development and coordination on risk-decisions.

- Monitoring on portfolio quality: checking existing and expected risk level, catching anomalies.

- Provisioning policy: monitoring and analysis on provisioning level (PD, LGD, EAD).

- Monitoring on risk-model performance: daily risk-filter monitoring, weekly-, monthly- reportment, score-model performance control.

- Risk-events investigations: fraud attack detection, IT-down catching (operational risks).

- Credit policy owner: development, actualizing, AB-test managing, updating. Matching with risk-engine specification.

- Risk-events history keeper: fixating and owing of company history of events affecting/explaining on risk level (incl seaonability, special campaigns, ne model implementation, AB-tests, etc. )

- Change management: participating, control and managing on full change implementation process ( change request - task clarification - development support - quality testing - production testing - final decision on using as - champion- )

- Risk-modeling: risk-kpi assessment, kpi-based decisions foundation.

- Business level risk-modeling: development on logical risk-rules and antifraud-rules, monitoring on social fraud information. Common with score-modeler - business understanding and expertise on main variables (top features) and correlations in score model.

- Existent + new data-sources: comparing, modeling on effect, assessment, trial-using coordination, integration managing.

- Risk cost management: assessment on profitability from risk-activities, data-sources costing-model optimization.

- Risk budgeting: participation in company budgeting from risk prospective - forecasting of provisions, approval-rate, default level, risk-model and collection costing.

- Team support: risk consulting, common projects, especially for verification and collection teams.

Technical Skills Required:

- Excel - advanced

- SQL: as business-user (basic and data-understanding level)

- Score modeling experience (any type of environment - R, Python, SS, SPSS, ets.)

- Math, tech education (ML, math statistics, probability theory)