Autonomous critical thinker, with broad analytical skills and over 5 years of experience with
conceptualizing, managing and applying problem solving skills to data projects.
Proficient engineer, with practice in data collection, processing, analysis, modeling,
deployment and communication through end-to-end data science projects done in large (50+
members) and international collaborations.
My area of interests include Pipeline Automation, Machine Learning, Analytics.
Please feel free to reach out if you believe I can be of help to you or the other way round.
*Self Recognized
* Supervised the development of credit limit and credit score card for finance department. * Research, development, tracking, and serving of demand forecast pipeline for demand planning. * Develop continous training and continous delivery using MLFlow and Metaflow for demand forecast. * End-to-End Market Insight pipeline using Airflow, Asprise API, Google drive, and Cloud Storage. * Developed Chatbot for customer interaction using LangChain, FastApi, and MLFlow. * Lead a team to develop monthly market insight reports for customers in Nigeria, and Ghana.
* Development of ETL & ML pipelines for extraction of trip records, and predicting trip cost estimation. * Experimentation, training, and deployment of causal model for trip incidence prediction in Nigeria. * Data extraction, transformation, and loading from Mongo to s3 datalake.
* Managed over 30 Artificial Engineers from across the globe, to develop AI solution for Agric-tech startup. * Organized weekly scrum meeting with AI engineers and present weekly report to non-stakeholders. * Trained over a 100 students on MLOps for AI engineers and data scientist.
* Trained a pre-trained resnet18|34|50 CNN models with enhanced images. * Build both automated machine learning models: IBM Watson; and non-automated machine learning models: Gradientboost, Random Forest, Support Vector, Prophet, and Linear-learner on Sagemaker. * Preprocessing satellite images using Histogram equalization techniques. * Scraping and wrangling of disaster response data.
* Generated insights & reports from the financial data for UNICEF/WASH projects in Nigeria. * Analyze geospatial data for project locations different regions of Nigeria. * Selecting and supervising teams for client's energy demands evaluation and presenting possible renewable energy solutions. * Trained teams in Uganda, and Sudan on management and utilization of a portal for Internet of Things products: Solar Cold-Chain Equipment, and IoT platform.
| Certificate | Date | Institution |
|---|---|---|
| Hands-on Airbyte | May, 2024 | Udemy Inc. |
| MSc in Big Data Technologies | March, 2024 | University of East London |
| Google Cloud Certified Professional Data Engineer | January, 2024 | Google Inc |
| Data Engineering Track | October, 2022 | Datacamp Inc |
| ETL in Python | August, 2022 | Datacamp Inc |
| Building Data Eng’g Pipelines in Python | September, 2022 | Datacamp Inc |
| Machine Learning Scientist with Python | December, 2023 | Datacamp Inc |
| Machine Learning(Health & Finance Track) | August, 2022 | Oxford ML Summer School |
| AWS Machine Learning Specialty | July, 2021 | CloudAcademy Inc |
| Google Project Management Certificate | April, 2022 | Cousera Inc |
| GitOps: Continuous Delivery on Kubernetes | September, 2022 | LinuxFoundation Inc |
| Customer Segmentation & A/B Testing | August, 2022 | Datacamp Inc |
| Credit Risk Modelling in Python | October, 2021 | Datacamp Inc |
| Advance NLP with spaCy | February, 2022 | Datacamp Inc |
| Bachelor of Engineering in Telecom. Eng'g | December, 2015 | Fed. Uni. Tech. Minna |
| Project Title | Description | Blog | Category |
|---|---|---|---|
| Sales Data Migration with Airbyte & Airflow. | In this project, customer sales transaction data were migrated from MySQL & Postgres to Bigquery & Snowflake using Airbyte. |
unpublished | Personal |
| Batch Pipeline to pull Public Health for clustering analysis using Python & Prefect. | The Orchestrated pipeline was developed to pull records from data warehouse to data lake for clustering analysis. | unpublished | Personal |
| End-to-End market insight pipeline using Metaflow, Asprise API, and Google Cloud. | In this project, customer invoices are collated, and dropped on Google drive and the pipeline preprocess and extract the data for purchase analysis. |
unpublished | Company |
| End-to-End market insight pipeline using Metaflow, Asprise API, and Google Cloud. | In this project, customer invoices are collated, and dropped on Google drive and the pipeline preprocess and extract the data for purchase analysis. |
unpublished | Company |
| Research, development, tracking, and serving of demand forecast for demand planning. | This project aims at providing demand forecast for the operations team through research and development of an automated end-to-end demand forecast pipeline. |
unpublished | Company |
| Developed Chatbot for insight analysis using LangChain, FastApi, and MLFlow. | This project is aimed at providing immediate insights on sales to both external customers and internal users such as operation department. |
unpublished | Company |
| Bed utilization rate | The aim of the project is to help clinic estimate resource utilization durion Covid in USA. |
medium | Hackathon |
| Ochestrated ETL Pipeline for Public Health Data | This is a development of efficient data ingestion pipeline for public health data using Kestra & Poetry. |
unpublished | Personal |
| ETL Pipeline for Market Insight Analysis | This project involves loading gdrive with invoice images, preprocessing, and extracting the content of the images. Transforming the data and loading the data to Google cloud storage and Gdrive. And ochestrated with metaflow. |
unpublished | Company |
| Data modelling ochestration with Dagster | This project demonstrate how to utilize ETL pipeline for data ingestion using Dagster. |
unpublished | Personal |
| Developed credit risk and credit score for the finance department. | An adjustable credit risk/credit model was developed using machine learning for the finance department. |
unpublished | Company |
A presentation on 'Outlier Detection'.
A sub-topic on 'Introduction to Advance Machine Learning.'
Last updated 3 mins ago
A presentation on 'Time Series Data'.
A sub-topic on 'Introduction to Advance Machine Learning.'
Last updated 3 mins ago
Guides from implemented AI project.
Last updated 3 mins ago