Sharjeel Jalil Albasit
Senior Data Analyst with 8 years of experience in Banking, Q-Commerce, and Mobility platforms across Pakistan and the Middle East. Built prediction models and optimization tools that reduced churn, shaped pricing strategy, and drove revenue growth.
ETA Prediction Model
5-stage segmented ETA with hierarchical Bayesian smoothing, OSRM calibration, and recency-weighted medians. Validated on 137K orders, MAE 8.49 minutes.
Credit Risk Scoring and Limit Engine
MLP neural network scoring 891K bank customers with 5-tier risk categorization, proxy income estimation, and credit limit determination.
Demand Control System
Zone-level stress management with progressive search and listing radius shrink, Butler shutdown, and customer-facing delivery Choice tiers.
Courier Shift Optimization
Demand-aligned shift scheduling replacing fixed templates. Median demand forecasting, greedy selection, dispatch simulation. Utilization 0.8 to 1.1 orders/hour.
Vendor Churn Prevention Engine
Predicts which restaurants will go inactive using operational KPIs. Intervention on flagged vendors reduced churn by roughly 62% across 17K vendors.
Customer Pricing Intelligence
Infers customer personas from trip geography using OpenStreetMap, then predicts willingness-to-pay. Outputs pricing multipliers from 1.00x to 1.15x.
Smart Ride Assignment Engine
Ride acceptance prediction replacing nearest-driver dispatch with ML-driven ranking using driver behavioral odds, route patterns, and geometric features.
- Developed a food prep time prediction model with 85% offline accuracy for dispatching decisions
- Customer segmentation and contextual campaign design that lifted conversion by 5%
- Shift optimization model that increased courier utilization from 0.8 to 1.1 orders per active hour
- Stress control system adjusting search radius, delivery distance, and markup tiers during peaks
- Data-driven device allocation strategy that improved merchant rescue rate by 42% in Dubai and Jeddah
- Automated 30+ finance reports, cutting payout reconciliation time by 25%
- Fixed gaps in A/B testing framework including KPI significance and guardrail checks
- Product event instrumentation for full funnel visibility, improving final-stage conversion by 10%
- Lifted marketing campaign conversion from 2% to 15% with lifecycle-based targeting
- ML models for power user prediction, increasing average daily bike taxi trips by 13%
- Smart matchmaking algorithm that cut ride acceptance time by 5 minutes
- Dynamic surge pricing engine that increased processing commission by 5% within 2 weeks
- Reduced vendor churn by 62% with a prediction model that flagged high-risk partners for intervention
- Improved Vendor NPS by converting 18% of detractors to promoters
- Managed restaurant closures and supply constraints across 92 zones
- Daily order forecasts and refined penalty rules, cutting order fail rate by 7%
- Mobilized PKR 1B in deposits from 4K customers in 3 weeks using deposit RFM analysis
- Reduced credit card attrition by 23% in under 4 months with predictive churn modeling
- Predicted and reactivated 50K+ dormant and at-risk deposit accounts
- Default prediction model assessing 1M customers for digital loans at 78% accuracy
