Badges
Certifications
Work Experience
DATA SCIENTIST
SUNSEA ENERGY LLC• May 2018 - Present
Goal: CUSTOMER SEGMENTATION; Project was for customer segmentation, result for project is to classify potential customers from company’s data set, using logistic Regression algorithm , Designed a GEO – DEMOGRAPHIC SEGMENTATION MODEL , to reduce customers churning ( leaving the company). Goal: Price Prediction Model for Sunsea Products ; Project was for price prediction for sales of Sunsea Products to customers , result for project is for the model to predict the price of the products based on the different utilities and regions of the diverse customers from company’s data set , using Tensor Flow and keras . I DESIGNED A PRICE PREDICTING MODEL to predict the best price for customers in comparation with competitor’s prices. Responsibilities: ● Provided the architectural leadership in shaping strategic, business technology projects, with an emphasis on application architecture. ● Working with Scrum as a development Team member using its framework for developing, delivering, and sustaining complex machine learning models and deep learning models. ● Utilized domain knowledge and application portfolio knowledge to play a key role in defining the future state of large, business technology programs. ● Developed MapReduce/Spark Python modules for machine learning & predictive analytics in Hadoop on AWS. Implemented a Python-based distributed random forest via Python streaming. ● Created ecosystem models (e.g. conceptual, logical, physical, canonical) that are required for supporting services within the enterprise data architecture (conceptual data model for defining the major subject areas used, ecosystem logical model for defining standard business meaning for entities and fields, and an ecosystem canonical model for defining the standard messages and formats to be used in data integration services throughout the ecosystem). ● Used Pandas, NumPy, seaborn, SciPy, Matplotlib, Scikit-learn, NLTK in Python for developing various machine learning algorithms and utilized machine learning algorithms such as linear regression, multivariate regression, naive Bayes, Random Forests, K-means, & KNN for data analysis. ● Conducted studies, rapid plots and using advance data mining and statistical modelling techniques to build solution that optimizes the quality and performance of data. ● Demonstrated experience in designing and implementation of Statistical models, Predictive models, enterprise data model, metadata solution and data life cycle management in both RDBMS, BigData environments. ● Analyzed large data sets apply machine learning techniques and develop predictive models, statistical models and developing and enhancing statistical models by leveraging best-in-class modeling techniques. ● Worked on database design, relational integrity constraints, OLAP, OLTP, Cubes and Normalization (3NF) and De-normalization of database. ● Worked on customer segmentation using an unsupervised learning technique - clustering. ● Utilized Spark, Scala, Hadoop, HBase, Kafka, Spark Streaming, MLLib, Python, a broad variety of machine learning methods including classifications, regressions, dimensionally reduction etc. ● Tested Complex ETL Mappings and Sessions based on business user requirements and business rules to load data from source flat files and RDBMS tables to target tables. Environment: AWS, R, Python, HDFS, OLTP, Oracle 12c, Hive, OLAP, DB2, MS Excel, Map-Reduce, SQL, XML, MLlib, Regression, Cluster analysis, Random forest, XML, Python, Data Mining, Seaborn, Jupyter, TensorFlow, K-means.
DATA SCIENTIST
FIRST BANK OF NIGERIA • July 2012 - April 2020
Client: First Bank of Nigeria Limited, MARINA, LAGOS April 2012 – April 2018 Role: Data Engineer /scientist Goal: CREDIT CARD FRAUD DETECTION WITH MACHINE LEARNING; To build a classifier that will detect credit card fraudulent transaction and separate them from non-fraudulent transactions using various algorithms like decision trees, Logistic regression, Artificial Neural network, Gradient Boosting Classifier. Goal: MONEY LAUNDERING (FINANCIAL FRAUD) DETECTION WITH MACHINE LEARNING; To build a classifier that will detect credit card fraudulent transaction and separate them from non-fraudulent transactions using various algorithms like decision trees (isolation forest), Logistic regression. Goal: FRAUDULENT PURCHASES(DETECTION) WITH MACHINE LEARNING; To build a classifier that will detect credit card fraudulent transaction and separate them from non-fraudulent transactions using various algorithms like decision trees (isolation forest), Logistic regression. (isolation forest), Logistic regression. Goal: FRAUDULENT INSURANCE CLAIMS (DETECTION) WITH MACHINE LEARNING; To build a classifier that will detect credit card fraudulent transaction and separate them from non-fraudulent transactions using various algorithms like decision trees (isolation forest), Logistic regression. Goal: SALARY INCREASE PREDICTION FOR STAFFS BASED ON YEARS OF EXPEREIENCE; To build a model that predicts salary increase of staffs, to find correlation between salaries and years of experience, using ordinary least squares (ols, linear regression), logistic regression. Goal: PROFIT PREDICTION MODEL; To build a model to show which branch to invest in and which branch to close , main criteria is profit , to show correlation between profits and months that have been spent on different expenses , using Linear Regression, Logistic Regression . Goal; CUSTOMER GEO SEGMENTATION MODEL OF THE BANK CUSTOMERS TO PREVENT CHUNNING; which customer is likely to leave or which customer is likely to stay, designing a geodemographic segmentation model, Logistic Regression, backward elimination, correlation matrix and Multicollinearity Intuition. Responsibilities: Worked independently and collaboratively throughout the complete analytics project lifecycle including data extraction/preparation, design and implementation of scalable machine learning analysis and solutions, and documentation of results. Performed statistical analysis to determine peak and off-peak time periods for ratemaking purposes Conducted analysis of customer data for the purposes of designing rates. Identified root causes of problems and facilitated the implementation of cost-effective solutions with all levels of management. Application of various machine learning algorithms and statistical modelling like decision trees, regression models, clustering, SVM to identify Volume using Scikit-learn package in R. Hands on experience in implementing Naive Bayes and skilled in Random Forests, Decision Trees, Linear and Logistic Regression, SVM, Clustering, Principal Component Analysis. Performed K-means clustering, Regression and Decision Trees in R. Worked on Text Analytics and Naive Bayes creating word clouds and retrieving data from social networking platforms. Pro-actively analyse data to uncover insights that increase business value and impact. Support various business partners on a wide range of analytics projects from ad-hoc requests to large-scale cross-functional engagements Prepared Data Visualization reports for the management using R Hold a point-of-view on the strengths and limitations of statistical models and analyses in various business contexts and can evaluate and effectively communicate the uncertainty in the results. Application of various machine learning algorithms and statistical modelling like decision trees, regression models, SVM, clustering to identify Volume using Scikit-learn package in python, MATLAB. Worked on different data formats such as JSON, XML and performed machine learning algorithms in Python. Conducted approach analysis in multiple ways to evaluate approaches and compare results. Developed statistical reports with Charts, Bar Charts, Box plots, Line plots using PROC SGPLOT, PROC GCHART and PROC GBARLINE. Used SAS Procedures like PROC FREQ, PROC SUMMARY, PROC MEANS, PROC SQL, PROC SORT, PROC PRINT, PROC Tabulate, PROC UNIVARIATE, PROC PLOT and PROC REPORT to generate various regulatory and ad-hoc reports. Created reports in the style format (RTF, PDF, and HTML) using SAS/ODS. Built complex DAX formulas in Microsoft Power Bi for various business calculations. Created Bar Charts which is compiled with data sets and added trend lines and forecasting on future trend of the financial performance. Possess good technical skills in SAS programming language for different SAS solutions that are utilized to analyse and generate files, tables, listings, graphs, validations, reports and documentation. Environment: MS Azure, HDFS, SAS, Python, Pyspark, MapReduce, Hive, UNIX, XML, JSON, SQL server, T-SQL, PL/SQL, Oracle 12c.
Education
University of Benin
Business Administration, MBA• January 2006 - May 2011
University of Benin
Computer Science, BS• January 1999 - June 2004