ADEREMI ABIOLA

Accomplished 87% churn prediction accuracy by building a Random Forest classifier on 15,000+ customer records from Lloyds Banking Group dataset (feature engineering on 12 behavioral variables including transaction frequency, account tenure, and service usage patterns), resulting in identification of top 500 at-risk customers worth $2.3M in annual revenue for targeted retention campaigns.

Accompl

Built a churn prediction model (Random Forest) on 15,000+ customer records, achieving 87% accuracy and identifying top at-risk customers for retention campaigns. Designed interactive Tableau dashboards and automated Python ETL pipelines to improve decision speed and reduce manual CSV log parsing.

Accomplished 92% reduction in report turnaround time (72 hours → 6 hours) by building 10+ automated Power BI dashboards integrated with CRM, ERP, and marketing platforms via SQL queries and Power Query ETL pipelines, resulting in real-time KPI visibility for 3 department heads and elimination of 40+ hours monthly manual reporting work.

Accomplished 25% decrease in data errors by implementing sta

Engineered predictive classification models (Random Forest, XGBoost, Logistic Regression with GridSearchCV) achieving 82% average accuracy, along with reusable Python preprocessing functions. Performed NLP sentiment analysis on unstructured feedback to identify product improvement opportunities and documented end-to-end ML workflows for deployment-ready code.

Accomplished 82% average model accuracy across 4 classification projects by engineering 15+ predictive features (temporal patterns, interaction terms, polynomial transformations) and implementing ensemble methods (Random Forest, XGBoost, Logistic Regression with hyperparameter tuning via GridSearchCV), resulting in "Excellent Performance" rating and models deployable for real-world decision suppor

Accomplished 60% reduction in client KPI tracking time by building 3 automated Power BI dashboards and 2 Tableau visualizations with real-time data refresh schedules (hourly updates via API connections), resulting in self-service analytics that eliminated 12+ hours weekly of manual report generation for e-commerce and fintech clients.

Accomplished identification of 2 high-value customer segments

Created 6 self-service Power BI dashboards with drill-down capabilities, automated SQL refresh schedules, and role-based access, reducing manual reporting effort by 70%. Conducted data quality audits that recovered $15K by identifying billing inconsistencies and integrated 5 data sources into unified dashboards with advanced DAX measures.

Accomplished 70% reduction in manual reporting effort (10 hours → 3 hours weekly) by building 6 self-service Power BI dashboards with drill-down capabilities, automated SQL query refresh schedules, and role-based access controls for 5 department heads, resulting in 280+ hours annual time savings and shift from reactive reporting to proactive analysis.

Accomplished $15K revenue recovery by identi

Pursuing a B.A. in Finance focused on using data and research insights.

Passionate about data, research and insights

Mastering statistical analysis and mathematical modelling to uncover meaningful patterns in complex datasets

Applying machine learning and predictive modelling to forecast trends and business outcomes

Creating clear, impactful data visualisations and dashboards to communicate insights to stakeholders

Developing programming skills in data science tools for data manipulation and analysis

Transfo