PUBLICATIONS
Ogundepo, E. A., & Yahya, W. B. (2023). Performance analysis of supervised classification models on heart disease prediction. Innovations in Systems and Software Engineering, 1-16. doi: https://doi.org/10.1007/s11334-022-00524-9
Ogbuju E., Banjo O., Ogundepo E.A., Folorunso S., Oladipo F. (2022). A Dataset of Location-Based Tweets in Africa On Covid-19 Outbreak. The Journal of Information Systems & Operations Management, 16(1), pp. 200-208.
Folorunso, S. O., Ogundepo, E. A., Awotunde, J. B., Ayo, F. E., Banjo, O. O., & Taiwo, A. I. (2022). A Multi-Step Predictive Model for COVID-19 Cases in Nigeria Using Machine Learning. In Decision Sciences for COVID-19 (pp. 107-136). Springer, Cham. doi: https://doi.org/10.1007/978-3-030-87019-5_7
Folorunso, S. O., Awotunde, J. B., Banjo, O. O., Ogundepo, E. A., & Adeboye, N. O. (2022). Comparison of Active COVID-19 Cases per Population Using Time-Series Models. International Journal of E-Health and Medical Communications (IJEHMC), 13(2), 1-21. doi: http://doi.org/10.4018/IJEHMC.20220701.oa6
Folorunso, S., Ogundepo, E., Basajja, M., Awotunde, J., Kawu, A., Oladipo, F., & Ibrahim, A. (2022). FAIR machine learning model pipeline implementation of COVID-19 data. Data Intelligence, 4(4), 971-990. doi: https://doi.org/10.1162/dint_a_00182
Oladipo, F., Folorunso, S., Ogundepo, E., Osigwe, O., & Akindele, A. (2022). Curriculum development for FAIR data stewardship. Data Intelligence, 4(4), 991-1012. doi: https://doi.org/10.1162/dint_a_00183
Ghardallou, M., Wirtz, M., Folorunso, S., Touati, Z., Ogundepo, E., Smits, K., ... & van Reisen, M. (2022). Expanding non-patient COVID-19 data: Towards the FAIRification of migrants’ data in Tunisia, Libya and Niger. Data Intelligence, 4(4), 955-970. doi: https://doi.org/10.1162/dint_a_00181
Adekanmbi, O., Oyewusi, W. F., & Ogundepo, E. (2020). Real-Time Crowdsourcing of Health Data in a Low-Income Country: A Case Study of Human Data Supply on Malaria First-Line Treatment Policy Tracking in Nigeria. In CSW@ NeurIPS (pp. 14-18). http://ceur-ws.org/Vol-2736/paper3.pdf
Ogundepo, E., Folorunso, S., Adekanmbi, O., Akinsande, O., Banjo, O., Ogbuju, E., Oladipo, F., Abimbola, O., Oseghale, E., & Babajide, O. (2020). An Exploratory Assessment of a Multidimensional Healthcare and Economic Data on COVID-19 in Nigeria. Data in brief, 106424. doi: https://doi.org/10.1016/j.dib.2020.106424
Ogundepo, E. A. & Fokoué, E. (2020). An empirical demonstration of the no free lunch theorem. Mathematics for Applications, 8(2), 173–188. doi: https://doi.org/10.13164/ma.2019.11
Akande, O.K., Olagunju, R.E., Aremu, S.C., & Ogundepo, E.A. (2018). Exploring Factors Influencing of Project Management Success in Public Building Projects in Nigeria. YBL Journal of Built Environment, 6(1), 47-62. doi: https://doi.org/10.2478/jbe-2018-0004
Contributions
bulkreadr package: bulkreadr is an R package that simplifies and streamlines the process of reading and processing large volumes of data. It allows users to read multiple sheets from Microsoft Excel/Google Sheets workbooks and multiple CSV files from a directory efficiently. https://gbganalyst.github.io/bulkreadr
forstringr package: Forstringr enables complex string manipulation in R, especially to those more familiar with LEFT(), RIGHT(), and MID() functions in Microsoft Excel. The package combines the power of stringr with other manipulation packages such as dplyr and tidyr. https://github.com/gbganalyst/forstringr
ralger package: ' ralger' aims to facilitate web scraping in R. The user can extract a vector with scrap(), a tidy dataframe with tidy_scrap(), a table with table_scrap(), and web links with weblink_scrap(). https://cran.r-project.org/web/packages/ralger/index.html
Big Book of R: The most extensive collection of R books. https://www.bigbookofr.com
Mastering Shiny Solutions: This book offers solutions to the exercises from Hadley Wickham’s book Mastering Shiny. https://github.com/r4ds/mastering_shiny_book_solutions
Co-editor: Beginners’ Artificial Intelligence & Python Programming Book for Primary and Junior Secondary Schools. https://www.datasciencenigeria.org/ai-beginners/
COVID-19 data repository: COVID-19, healthcare facilities, and economic related data in Nigeria, Mendeley Data, https://data.mendeley.com/datasets/8h5rtbbx7m/2
COVID-19 data repository: Location-based Tweets in Africa on COVID-19 Pandemic, Mendeley Data, http://dx.doi.org/10.17632/c8x5tpvzmk.1
DATA SCIENCE PROJECTS
Data4Governance Challenge at the CCHub Lagos, Nigeria
Title: The Impact of Flood on Agriculture: A case study of Ibadan city
Date: February, 2020
CcHUB in partnership with the WorldBank, the Bill and Melinda Gates Foundation, the European Union, Korea International Cooperation Agency, and the Department for International Development hosted the Data4Governance challenge. This event was an 8-day design for development hackathon which started on February 17 and ended on February 26, 2020. Our team, Data Findars, worked on Impacts of Flood Hazards on Agriculture and Settlement. Our solution which was among the top 8 can be found here and executive report here.
Data Science Capstone Project for Microsoft Professional Programme in Data Science
Title: Mortgage Loan Approvals Prediction from Government Data.
Date: May- June, 2019
The project considers how demographics, location, property type, lender, and other factors are related to whether mortgage application across the United States was accepted or denied. We trained a Catboost model on 500,000 mortgage loan applications and noticed that lender, applicant income, loan purpose, loan amount and state code have a significant effect on the mortgage loan approval. The prediction results whose code file can be found here achieved a public score of 0.7330 out of the benchmark of 0.7350 and you can also read the executive report here.
Date: March- April, 2019
A data-driven challenge organized by Deep learning IndabaXMorocco tested ML skills on a real-case problem. The Github page which can be found here used various catalogs of machine learning models to predict the class labels of heart disease data on the validation dataset. We evaluated the performance of each model with logloss metric and the model with the least logloss was used to predict the class label on the validation dataset. Our submission under GBG-IXM was ranked 1st among IXM groups.
A Comprehensive Empirical Demonstration of the No Free Lunch Theorem (NFLT) in Statistical Machine Learning
Date: November 2018- February 2019
In this project, we provided a comprehensive empirical demonstration of the NFLT by comparing the predictive performances of a wide variety of machine learning algorithms/methods on a wide variety of qualitative and quantitative different datasets. Our research work conclusively demonstrates great evidence in favor of the NFLT by using the overall ranking of methods and their corresponding learning machines. The github can be found here.
Statistical automation of tax analysis
Date: May - November, 2018
This project used tidyverse and some other R packages to create an automated data portal which included revenue collection statistics, registration statistics, HR statistics, cost statistics, etc. for the Rwanda Revenue Authority.