Creative Problem-Solving
I enjoy thinking "outside the box" to find non-obvious patterns. My curiosity drives me to look beyond the surface of a dataset to find the narrative hidden within.
Hi!
I am an Industrial Engineer currently completing my Master’s in Data Science. Throughout this journey, I’ve discovered a genuine passion for extracting value from data, specifically where business meets technology: Machine Learning and AI to optimize customer behavior analysis, product performance, market segmentation, and e-commerce optimization.
Driven by curiosity, I’ve complemented my formal studies with self-taught projects, focusing on building practical solutions that demonstrate how data can be translated into real business impact.
I enjoy thinking "outside the box" to find non-obvious patterns. My curiosity drives me to look beyond the surface of a dataset to find the narrative hidden within.
I believe that how insights are communicated is just as important as the analysis itself. I prioritize clarity and aesthetics to ensure data is not only accurate but also easy to act upon.
I focus on the "human layer" of technology. I know how to ask the right questions, whether it’s framing a business problem or crafting the perfect prompt to guide an AI.
I’m committed to the math behind the models. Whether it’s testing hypotheses or defining KPIs, I ensure every solution is backed by sound statistical principles.
A decision-making CRM agent that starts with raw customer metrics, infers lifecycle context, selects the right marketing objective, and generates complete three-email campaign flows via LLM.
Full analytics pipeline from raw transactions to dual-layer RFM segmentation and commercial buyer deep dives.
K-Means clustering combined with association rule mining to uncover which products are bought together, and by which customer types.
Combining retention, revenue concentration, and cohort behavior into a predictive layer that identifies customers worth retaining.
Multi-metric evaluation beyond headline KPIs — combining hypothesis testing, bootstrap intervals, and full-funnel analysis.
Reconstructing the full purchase funnel from raw event logs to identify exactly where users drop off, and which devices and acquisition channels drive conversions.