Emmanuel Isa

• Implemented comprehensive reporting systems for various key areas of the organization, including utilization, telemedicine, claims, providers, and diagnoses. These reports were generated using ICD10 coding standards, providing a consistent and informative view of the data. • As a specialist in data visualization, I developed Tableau dashboards for the corporate retention team to enable prompt access to critical revenue and upsell performance data. The dashboards were designed to be dynamic and real-time, providing a comprehensive view of team performance and contributing to the team's success, as demonstrated by consistently elevated NRR numbers exceeding 100%. • To enhance customer satisfaction, I created Tableau visualizations for monitoring CSAT scores from various sources including corporate clients, enrollees, and providers. This approach resulted in improved CSAT scores that consistently exceeded the company's threshold. I also developed visualizations for the brand and growth division to monitor important metrics such as MQLs, web sessions, online purchases, and ad analytics, resulting in a significant improvement in conversion ratios and eCommerce conversion rates. • I devised interactive Tableau dashboards for each division within the organization, enabling departments to monitor crucial performance indicators in real-time, leading to a noticeable boost in their overall performance. • Possessing proficiency in both Snowflake SQL and MySQL, I write complex SQL queries to extract meaningful insights from healthcare datasets. I fully utilize both database platforms being used by the company to deliver results that meet the organization's needs. • To support clinical decision-making, I created a geographical map visualization of medical claim volumes in Tableau. The map provided valuable insights into high-density areas, allowing for further investigation into granular data such as street names and neighborhoods.

• Led the Access Bank gamification project, where I was responsible for developing month-on-month optimization plans to drive customer engagement and increase transactions. My data-driven approach led to a remarkable increase in bank transactions and revenue by over 4000% in incremental figures. • Resurrected dormant bank accounts by conducting a thorough analysis of customer behavior and demographics, using data-driven optimization and contact strategies to improve customer retention through business intelligence. • Managed campaign data, conducted AB test analysis, cohort/segment analysis, and visualized campaign performance to provide insights into customer behavior and preferences. My expertise in SQL and Google Big Query enabled me to wrangle data effectively, while Google Data Studio provided the necessary tools for pattern detection and visualization.

• As a seasoned data scientist and analyst, I have had the privilege of spearheading several cutting-edge projects across the banking, foundation, and government sectors. At the United Bank for Africa, I led an advanced analytics project that involved integrating data from various sources and developing machine learning models using Azure Data Bricks. My responsibilities included developing customer segmentation models, customer lifetime value models, customer churn models, and survival analysis models. • At Zenith Bank, I served as a team lead for a data warehousing project, where I was responsible for designing data tables, and ETL processes, and supervising Power BI visualization reports. I also collaborated with a team to drive a Zenith Bank channels analytics project, which leveraged the power of Microsoft Azure to perform ETL and cloud computing. In this capacity, I was responsible for managing the Azure data factory account that contained the ETL and the Power BI online dashboard that contained the reports. I ensured the ETL pipelines in the data factory ran smoothly on a daily basis, and the dataset of the Power BI reports refreshed daily. • Additionally, I have collaborated with teams to deliver predictive analytics for Fidelity Bank and ALAT by Wema Bank on customer analytics, customer segmentation, product recommendation, and customer loan default, by building machine learning models on the data and visualizing the results with Microsoft Power BI to drive actionable insights. • Moreover, I have worked with the TONY ELUMELU FOUNDATION to perform data cleansing tasks using data quality services on Microsoft data quality client, SQL server integration services, and SQL server management system. Subsequently, I created visualizations on the cleansed data using Microsoft Power BI. • At African Prudential, I was part of a team that successfully deployed a full-stack Data Warehouse. My role included creating entity relation diagrams, logical models, and physical models for the warehouse, ETL for the data, and reporting and visualizing the data in the warehouse using Microsoft Power BI. • In addition, I developed a Power BI analytics solution for the Lagos State Government Ministry of Health. I was a key team player in analyzing and accessing key performance indicators, data generation for the model, integrating the data on a SQL server, and building and deploying the model. I also developed a Power BI analytics model for the Nigerian National Petroleum Corporation and the Department of Petroleum Resources.

• In this project, I developed and implemented two sophisticated pre-delinquency models, utilizing both the Random Forest Classifier and Neural Network algorithms on a complex loan dataset. The models were extensively trained and tested using the same dataset, and a thorough comparison of the models was conducted to arrive at a definitive conclusion regarding their efficacy. This process of supervised machine learning was carefully undertaken with the goal of optimizing the accuracy and efficiency of loan prediction. • Additionally, I employed unsupervised machine learning techniques to analyze a large dataset of loan applicants, using advanced statistical methods to perform dimensionality reduction via principal component analysis (PCA) on a data frame containing over two hundred features. Utilizing the industry-standard Sklearn's KMeans function, I effectively clustered the data, providing critical insights into patterns and trends among the customers who applied for loans. • Furthermore, I leveraged the robust capabilities of Google Big Query and Google Data Studio to analyze complex customer billing and loan data. Through this process, I extracted and analyzed data on clients who received their first loan within a specific timeframe, as well as data on the number of clients who took out loans in the subsequent months of that year. This approach provided valuable information to support data-driven decision-making, enabling my team to make informed business decisions based on comprehensive data analysis.