↩ Work / EXPERIENCE

Global Data Analyst.Employment

Period: Nov 2019 - Sep 2022
Company: GOZEM ↗

First data hire: built Gozem's analytics function from the ground up: GCP/BigQuery migration, monitoring automation, fraud-pattern detection, and marketing segmentation.

Led cloud migration to GCP, replacing legacy batch processing with a BigQuery-based data warehouse and scheduled ETL pipelines.
Built automated data pipelines for incentive payments, reducing a multi-day manual process to minutes through structured operational data and near real-time monitoring.
Implemented a fraud patterns database with automated daily collection monitoring, surfacing anomalies the same day they appeared and laying groundwork for later ML-based fraud screening.
Founded the analytics engineering function and grew a distributed team of 4, delivering automated dashboards, KPI reporting, and weekly market insights.
Refined Marketing segmentation and cohort analysis through a user profiling database, supporting targeted campaigns and retention analysis.

[•] PROJECTS & USE CASES

8 ENTRIES

Cloud migration to GCP & BigQuery warehouse

Result Migrated tens of terabytes in one quarter without interruption; the BigQuery warehouse and 50+ scheduled pipelines became the analytical foundation.

Problem / Need

The data infrastructure ran on legacy batch processes that couldn’t keep up with growing operational and analytical needs across countries.

Solution

Led the cloud migration of the entire data infrastructure to GCP, designing a BigQuery-based data warehouse with 50+ scheduled ETL pipelines and migrating tens of terabytes within a quarter without interruption.

Tools

GCP·BigQuery·Python·Cron·Scheduled BigQuery queries

Operational monitoring automation

Result Replaced a 2-day manual job with a 5–15 minute automated cycle for operational scenarios.

Problem / Need

Operations monitoring relied on a manual recurring job to spot business scenarios across markets, taking up to 2 days of analyst work per cycle and creating detection lag.

Solution

Automated the operational monitoring workflow within the first 6 months of the role. Python jobs querying PostgreSQL surfaced supply gaps, driver behaviour anomalies, fraudulent trip patterns, and other scenarios into Google Sheets for the operations team, replacing a 2-day manual job with a 5-15 minute automated cycle.

Tools

Python·PostgreSQL·Google Sheets

Incentive payment automation

Result Reduced a multi-day manual payment process to minutes, with structured logs and dispute trails for finance and support.

Problem / Need

The agent and partner incentive payment process took multiple days, with manual reviews creating delays, errors, and a heavy load on the finance team.

Solution

Built automated data pipelines for incentive payments combining structured operational data and near-real-time monitoring. Reduced a multi-day manual process to minutes, with structured logs and dispute trails for finance and support.

Tools

BigQuery·Python·Airflow·Looker Studio

Fraud patterns database & daily monitoring

Result Surfaced collection anomalies the same day they appeared and established groundwork for later ML-based fraud screening.

Problem / Need

Financial defaults from undetected fraud patterns were eroding margins, with no central knowledge base of known schemes or systematic daily collection monitoring.

Solution

Implemented a fraud patterns database fed by automated daily collection monitoring, surfacing anomalies the same day they appeared and laying the groundwork for the later ML-based fraud screening pipeline.

Tools

BigQuery·Python·Looker Studio

Marketing segmentation & cohort analysis

Result Gave Marketing structured rider and driver profiles, cohorts, and campaign signals for targeted analysis.

Problem / Need

Marketing campaigns were broadly targeted because the team lacked a structured user profiling layer, leading to low engagement and inefficient spend.

Solution

Built a profiling database covering riders and drivers, with RFM segmentation (recency, frequency, monetary) and cohort analysis used by Marketing for targeted campaigns. Translated cohort behavior into operational signals across retention, monetization, and re-engagement, supporting rider retention and growth.

Tools

BigQuery·Python·Looker Studio

Product and marketing data ingestion

Result Centralized product events, experiment data, and advertising performance in BigQuery for recurring product and campaign decisions.

Problem / Need

Product and Marketing teams lacked a shared analytical path across application behavior, A/B tests, campaign delivery, and audience profiles.

Solution

Built ingestion workflows from Firebase and Google Analytics, Google Ads, and Facebook/Meta Ads into BigQuery. Modeled the data for product analytics, A/B-test analysis, campaign performance, user profiling, and product-development decisions.

Tools

Firebase·Google Analytics·Google Ads·Facebook/Meta Ads·BigQuery

Seasonal driver-retention analysis

Result Supported an approximately 9% improvement in driver retention through season-aware incentive decisions.

Problem / Need

Driver availability and retention varied with the regional agricultural season, but incentive planning did not account for the timing and strength of that effect.

Solution

Analyzed driver activity against the regional agricultural calendar, identified the seasonal retention pattern, and translated the findings into incentive recommendations for Operations.

Tools

BigQuery·Python·Cohort analysis·Google Sheets

Business health monitoring & daily insights

Result Consolidated 20+ KPIs into a daily report used by country managers and top management for operational decisions.

Problem / Need

Country managers and top management lacked a single daily lens on business health across markets, with no consolidated KPI rhythm or recurring insight delivery.

Solution

Built business health dashboards in Google Sheets, transitioning to Looker Studio and Tableau after the BigQuery migration. Consolidated 20+ KPIs into a daily report spanning all business areas. Presented insights daily to country managers and top management, surfacing trends and anomalies for operational decisions.

Tools

Google Sheets·Looker Studio·Tableau·BigQuery

← Work