
Available for remote work worldwideAvailable for remote data science work · Worldwide
Data Scientist and Research Analyst.
I build machine learning models, research language technology, and help students get their research right.
In [24]: for name, model in models.items(): fpr, tpr, _ = roc_curve(y_test, model.predict_proba(X_test)[:, 1])

Oseni, O. S., Obanla, I. O., & Jimoh, T. A. (2026). Attention-based deep learning for early Parkinson’s disease detection with tabular biomedical data (arXiv:2602.07933). arXiv. https://doi.org/10.48550/arXiv.2602.07933
Five years in data science and research
100+ projects
Ongoing research
8+ citation styles
Data science
Machine learning for real business problems.
Credit risk, customer retention and security analytics, from first notebook to deployed model.
- Machine Learning Engineer· TechSTEPS Limited· 2023–2026
- Data Scientist· Armstrong Global Concepts· 2021–2023

Finance & credit risk
Credit risk: Lending Club default prediction
Default prediction on 2.2 million Lending Club loans issued 2007 to 2018, comparing logistic regression, decision trees, random forests and XGBoost.

Security
Explainable network intrusion detection
Intrusion classification with SHAP attributions, deployed as a Streamlit app so analysts can see why traffic was flagged.

Customer & people analytics
Employee attrition prediction
Attrition modelling on 1,470 employee records and 35 features, comparing logistic regression, decision trees, random forests and gradient boosting.

Security
Insider threat detection in email
Text classification to surface threatening messages, using a voting ensemble of logistic regression, decision tree and random forest, benchmarked against a Keras neural network.
Research
Language technology and machine learning in health.
NLP for low-resource African languages, starting with Yorùbá.
- Under review
Language data and policy · 2026
Auditing Yorùbá language datasets
How publicly available Yorùbá language datasets are licensed, documented and funded, and what that means for language-data policy and research funding in Nigeria.
- In progress
Natural language processing · 2026
Offensive language detection in Yorùbá social media text
Comparing classical machine learning with African-language transformer models, weighing accuracy against computational cost, and examining where models struggle with code-switching, informal spelling and missing diacritics.
- In progress
Natural language processing · 2026
A systematic review of NLP research on low-resource African languages
A systematic review of published natural language processing research on low-resource African languages, mapping what has been studied so far and where the gaps are.
- Preprint
Machine learning in health · 2026
Attention-Based Deep Learning for Early Parkinson's Disease Detection with Tabular Biomedical Data
Comparing attention-based deep learning models with established methods for detecting Parkinson's disease early from biomedical voice measurements.
Read on arXiv
Research & writing support
Studying in the UK, US or Canada? I can help.
Guidance, editing and feedback for university students worldwide, especially those new to their university's academic conventions.
Oseni, O. S., Obanla, I. O., & Jimoh, T. A. (2026). Attention-based deep learning for early Parkinson’s disease detection with tabular biomedical data (arXiv:2602.07933). arXiv. https://doi.org/10.48550/arXiv.2602.07933
- ReferencingHarvard, APA, Chicago, MLA, OSCOLA and more
- Editing and proofreadingClarity, structure and academic tone
- Dissertation planningQuestions, chapters and timelines
- Literature reviewsOrganising and critiquing sources
- Statistics and analysisMethods, R or Python, reporting
Let's work together.
Data science projects, research collaboration or academic support.