track record
fast growth outpaces fraud risk. i've spent my career in that gap - connecting data, operations, and compliance before it becomes a problem.
fraud and risk manager
Joined with no fraud infrastructure. Built the entire fraud framework end to end: chargeback procedures, investigation SOPs, UPI and RuPay transaction monitoring, cashback and coin fraud detection, Shop order and RTO monitoring, a block management feature, and a full fraud attack mitigation and recovery plan.
On the fraud typology side: identified and stopped ATO attacks by strengthening the SIM binding phase, iterating on friction and checks based on confirmed fraud user behaviour patterns. Caught first party fraud including RuPay card-to-cash abuse (mitigated with velocity checks and friction on refund flows), cashback claim fraud via a tech loophole (fixed with automated alerts), and RTO abuse in Shop (built pattern detectors for order, return, and geography based tracking).
Built an anomaly detection and monitoring layer covering onboarding spikes, transaction pattern deviations, error code shifts, and rewards velocity. When a fraud incident hit, worked with the data team to build a risk scoring model - mapping confirmed fraud user patterns across transaction amount, merchant category, error codes, and failure rates. The model kept evolving as new inputs came in, with a plan to integrate it directly into the rule engine as a live feedback loop. Also implementing an AI typology based pattern detector.
Compliance: built the compliance calendar, liaised with the InfoSec team end to end, and drove audit readiness for NPCI infosec audit, ISO 27001, PCI DSS, SOC 2, and DLSAR.
On the fraud typology side: identified and stopped ATO attacks by strengthening the SIM binding phase, iterating on friction and checks based on confirmed fraud user behaviour patterns. Caught first party fraud including RuPay card-to-cash abuse (mitigated with velocity checks and friction on refund flows), cashback claim fraud via a tech loophole (fixed with automated alerts), and RTO abuse in Shop (built pattern detectors for order, return, and geography based tracking).
Built an anomaly detection and monitoring layer covering onboarding spikes, transaction pattern deviations, error code shifts, and rewards velocity. When a fraud incident hit, worked with the data team to build a risk scoring model - mapping confirmed fraud user patterns across transaction amount, merchant category, error codes, and failure rates. The model kept evolving as new inputs came in, with a plan to integrate it directly into the rule engine as a live feedback loop. Also implementing an AI typology based pattern detector.
Compliance: built the compliance calendar, liaised with the InfoSec team end to end, and drove audit readiness for NPCI infosec audit, ISO 27001, PCI DSS, SOC 2, and DLSAR.
senior, risk and fraud analytics
Added the fraud layer: rebuilt onboarding controls, strengthened name-match algorithm accuracy, built anomaly monitoring dashboards based on hexcodes, and identified and blocked 3 high-fraud geographies. 35% reduction in fraud losses in 3 months. 30% reduction in high-risk signups.
manager, risk and fraud
Inherited raw Slack alerts - fraud patterns visible in location and transaction data. Built the complete fraud framework: rule engine on ClickHouse and Metabase, investigation procedures for every fraud type, chargeback procedures, and anomaly monitoring dashboards across transaction, onboarding, and rewards layers.
Key fraud typologies handled: first party fraud where bad actors used the platform to defraud innocent users, and rewards loophole abuse where gaps in cashback and referral logic were exploited at scale. Built detection and response workflows for both.
Also built the AML blacklist screening service on Whitebook to screen sanctioned individuals at onboarding - the first structured AML layer the product had. Migrated all users to a risk-aware onboarding flow. Established RBI regulatory reporting workflows. 90% reduction in fraud. Rs 5M in rewards abuse prevented.
Key fraud typologies handled: first party fraud where bad actors used the platform to defraud innocent users, and rewards loophole abuse where gaps in cashback and referral logic were exploited at scale. Built detection and response workflows for both.
Also built the AML blacklist screening service on Whitebook to screen sanctioned individuals at onboarding - the first structured AML layer the product had. Migrated all users to a risk-aware onboarding flow. Established RBI regulatory reporting workflows. 90% reduction in fraud. Rs 5M in rewards abuse prevented.
analyst, fraud and business intelligence
Detected key fraud patterns through data analysis and built a proof-of-concept model that shifted fraud operations from manual to analytics-driven. Built automated fraud detection that cut manual review time by 90% and improved suspicious transaction identification by 15%.
investigations specialist, sanctions compliance
Investigated suspicious accounts and trained a 120-member investigations team. Built compliance knowledge infrastructure used across a 200-member team.