Crypto Forecasting

Over $40 billion worth of cryptocurrencies is traded every day. They are among the most popular assets for speculation and investment. In this project, I've created virtualization to inspect the crypto one-by-one currency type and the machine learning model to forecast further market as the data...

Germany Rental

It's very hard for foreigners like me to find an apartment in Germany and we actually don't know how much do we have to pay per month. So, I dig deep in analysis, clean, virtualization, and creating a model by using Light Gradient Boost (similar to XGBoost but faster!) to predict the rental...

Fraud Analyst and Imbalanced Datasets

Anonymized credit card transactions are labeled as fraudulent or genuine. It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase. In this project, I'm trying to analyze the fraud...

Spanish Train

Rail transport in Spain operates on four rail gauges and services are operated by a variety of private and public operators. The total route length in 2012 was 16,026 km (10,182 km electrified). I'm trying to analyze the trend of the train usage through by using time as the index. We could know...