Hi, I'm Basharat.
Data scientist and analytics engineer in New York City. Payments, fraud, settlement and reconciliation data; metric definitions and semantic layers; experimentation and causal inference; LLM evaluation. Open to Data Scientist, Analytics Engineer, Senior Data Analyst, Business Operations / Strategy & Operations, and Strategic Finance analytics roles, in New York or remote US.
- At Geidea, Saudi Arabia's largest payments processor, I built real-time ML anomaly detection on 1M+ daily payment transactions to catch fraud and settlement errors. It evolved into production fraud models.
- My merchant churn prediction and revenue forecasting informed a tiered retention strategy that cut merchant churn from 35% to about 10% on a $5M+ revenue portfolio.
- Automated collections pipelines I built at Geidea contributed to $8M+ in additional annual profit.
- Through my own consulting practice I was the CEO's data person at Rime, a Saudi edge-AI retail camera startup, where I shipped an 11-model dbt migration across a multi-tenant Snowflake warehouse (50+ client schemas) with reconciliation built from zero.
I am a Graduate Assistant in AI Implementation at Mercy University in New York (M.S. Business Analytics, GPA 4.0, Aug 2026). Before Geidea I was a Senior Data Consultant at EY. Full experience.
Focus areas
- Data scientist for payments, fraud and risk analytics in New York
- Analytics engineer with dbt, Snowflake and semantic-layer experience
- Reconciliation and settlement data: ledgers, payouts and card networks
- Data scientist for LLM evaluation and AI measurement
- Business operations and strategic finance analytics
- Data scientist for growth, monetization and retention
- Data quality and observability: catching failures that look healthy
- Forecasting AI and usage-based spend
- Experimentation and causal inference: when the metric decides the answer
- Analytics engineer for semantic layers and metric definitions
Public work
- Ledger integrity under agent-speed traffic: Netting hid $32,732 (46%) of $71,570 gross error; a retry with a regenerated idempotency key was caught 0 of 53 times and is 93% of undetected dollar-hours.
- Merchant freeze economics: 60,000 merchants; the 98%-recall freeze policy nets -$9.1M versus freezing nobody; cutting review time from 3 days to 1 is worth +$4.5M, more than a 2-point AUC gain (+$3.3M).
- Queue economics for a fraud and compliance review team: Alert recall 85.1% to 80.0%, dollar recall 76.8% to 93.0%, total cost -54%.
You can reach me at sabasharat.ali@gmail.com.