Machine Learning
Machine Learning House Prediction
A neural network that grouped houses into price bands from their feature data.
The brief
What needed to be solved.
Property data is hard to scan quickly when the goal is to sort houses, not price every one by hand.
The model needed to turn feature patterns into clear price categories.
The constraint
What made it interesting.
I treated it as a classification problem with a real use case: faster screening and better market grouping.
The work focused on making the model output easy to use in a property workflow.
The build
What was assembled.
TensorFlow model experiments.
Feature-based classification setup.
Output shaped around price tiers.
Project write-up aimed at applied ML work.
The result
What changed after it ran.
Added a clear machine learning project to the portfolio.
Showed model work tied to a practical decision task.
Expanded the project mix beyond automation and workflows.
Stack
Read next
Data Systems
Analytics Documentation Practice
Ten documents, eighty-seven pages, one shared template. Three case studies in how raw operational data becomes decision-ready output: a Nigerian marketplace, a distributor, and a retail bank. The documentation discipline is what is being demonstrated: findings framed for executives, models explained for engineers, and runbooks written for the moment the analyst is not in the room.
Read case study →Data Pipeline
X Profile Scanning Pipeline
A vetting workflow that ran for two days unattended and returned 20,509 X profiles with verification status, follower counts, and region data filled in. Python, Playwright, openpyxl. Replaced a job that would have taken a small team weeks.
Read case study →