Data Analyst (ex-Accountant) | SQL · Python · Tableau · Excel
Turning financial rigor into customer, retention & growth insights.
I bring an MSc in Financial Accounting and hands-on junior accounting experience into data analytics, which means my projects don't just find patterns, they translate them into revenue, risk, and ROI numbers stakeholders actually act on.
SQL Python (pandas, seaborn, scikit-learn) Tableau Excel Snowflake Jupyter Notebook
Olist E-Commerce Funnel Analysis
SQL · Tableau · 104K+ orders
Problem: Olist, a Brazilian e-commerce marketplace, was losing revenue at multiple stages of the customer funnel, from cart abandonment through delivery delays, with no consolidated view of where or why orders were dropping off.
Recommendations:
- Prioritize fixing logistics bottlenecks in the regions/carriers responsible for the bulk of delays tied to R$1.95M in at-risk revenue
- Implement proactive delivery-delay notifications to reduce churn from poor delivery experience
- Use the Tableau dashboard as an ongoing operational monitoring tool, not a one-time analysis
Olist Customer Segmentation (RFM)
Python · pandas · Jupyter · 96,475 customers
Problem: Olist had no systematic way to differentiate high-value customers from one-time or lapsing buyers, making retention and marketing spend inefficient.
Recommendations:
- Launch targeted win-back campaigns for the high-value-but-lapsing segment, the R$3.07M lost high-value segment is the highest-ROI group to re-engage
- Build loyalty/VIP treatment to protect the concentration of value within the R$15.4M in segmented revenue
- Shift low-frequency/low-monetary segments to automated, lower-cost email flows rather than high-touch spend
Telecom Customer Churn Analysis
SQL · data cleaning & validation
Problem: The telecom provider was losing customers to churn without a clear, data-backed understanding of which profiles or behaviors were the strongest predictors — making retention efforts reactive rather than targeted.
Recommendations:
- Focus retention resources on the segments most strongly linked to churn, addressing $1.67M in revenue at risk
- Introduce early-warning triggers (usage drop-offs, support ticket spikes) for proactive intervention
- Test targeted incentives on high-risk segments instead of broad-based offers to improve retention spend efficiency
Data analyst roles in media, marketing,finance and growth analytics, where I can pair statistical rigor with a business/finance lens.
📍 Tokyo, Japan · ✉️ nothabomoyo07@gmail.com