π Hi Contra β Iβm Lilya, a Data Scientist working at the intersection of retail, demand forecasting, and promotion analytics.
My recent work focuses on SKU-level forecasting, where small modeling choices have a big business impact:
β’ π¦ Improving SKU-level demand forecasts for planning & inventory
β’ π Approximating the pull-forward effect of promotions
On the technical side, I work end-to-end:
β’ Time-series & ML forecasting
β’ Promo, price & calendar feature engineering
β’ PySpark batch pipelines & MLflow tracking
π‘ Open to freelance or contract projects around demand planning, retail analytics.
Happy to connect π
I engineered a large-scale package-network intelligence pipeline using Azure Databricks and PySpark. The system joined approximately 4.5 billion historical records and transformed them into reusable fingerprint signals covering package movement and network behavior.
I developed time-windowed feature logic using native Spark expressions rather than Python UDFs, preserving distributed performance at scale. The pipeline produced an approximately 200-million-row fingerprint dataset and a 22-million-row operational output that classified package activity along a cold-to-hot temperature scale.
The resulting signals supported downstream monitoring, prioritization, and operational analysis. The architecture shown here is a sanitized representation; client identifiers, proprietary schemas, infrastructure paths, and business rules have been removed.
The pipeline focuses onΒ data quality, scalability, and analytics readiness, converting raw transactional data into a clean, trusted fact table suitable for BI and reporting.
https://github.com/antara-1505/Sales-Analytics-System
0
79
Problem:
Users needed a faster way to find the most relevant counselor based on specialization and available data.
Solution:
Built a recommendation workflow using PySpark for data processing and Redis for fast lookup and recommendation serving.
Tools:
Python, PySpark, Redis, Docker, Docker Compose
Result:
Created a containerized recommendation system that processes counselor data and returns relevant matches efficiently.