Engineer & Junior Data Scientist. Having more than two years of experience in Machine Learning with Python using Jupyter Notebook through Anaconda, Kaggle, and Google Cloud Platform. Sound exposure to Data Preprocessing, Data Analysis techniques like Data Visualization, Feature Engineering, and Statistical Analysis; and model designing with Machine and Deep Learning algorithms.
Besides, replicated a journal paper ( Beijing Housing Price Prediction via Improved ML Techniques) for estimating London residential prices for one of the client master thesis involving geospatial data, transaction data, and macroeconomic data.
The research regarding estimating London Housing prices is based on UK transaction price paid data with adding some colors like integrating macroeconomic indicators (GDP, inflation, Employment and Unemployment, and Consumer Price Index),subways (within 0.5,1.0 & 2.0 miles property radius), bus stops (within 0.5 miles property radius) and supermarkets or retail stores (within 0.5,1.0 & 2.0 miles property radius). We all know that economics is connected to everything. So it can affect the property prices. Similarly, with more facilities in an area can impact the property price too. So the purpose is to see, whether they affect the house prices. Our base line is the transaction data. Then we add the other data one by one and check the predictions.
I will share that work on your request.