If you were one of the unfortunate passengers who boarding that Titanic ship, how confident are you to be survived? Well, if you have watched the James Cameron's Titanic movie (who haven't?!), the scene where Jack had to let go of Rose to that lifeboat must be called to your mind. You may notice that the lifeboats were dominated by women. But, is the movie really portray the true event? To prove that gender really influenced the survivability chance, we make use the titanic dataset from Kaggle to interpretate which factors contribute and to make a model to predict the passengers survival.

The project aims to make a point prediction model by using machine learning. I use the dataset from fantasy.premierleague.com, understat.com and club elo.com from the 2018/2019 and 2019/2020 season from more than 150 players. The data combined from those sources giving variables such as the player form, team form, home or away fixture, Elo ratings, expected goals per 90 minutes or even the time when the match happened.

Have you ever wonder how online transportation companies decide their price? Is the price spread equally throughout the time? or maybe distincted area priced differently? If we follow the basic economic rule, we all would agree that the price mainly will be influenced by the order demand (beside the availability of the driver). Higher demand means higher prices. And for sure, the demand would not be equally same through the time and through different places. In this case, we are provided a real-time transaction dataset from a motorcycles ride-sharing service by Algoritma Data Science team. With this dataset, we are going to help them in solving some forecasting problems in order to improve their business processes, including the pricing system and the driver availability. It’s almost the end of 2017 and we need to prepare a forecast model to help the company ready for the end year’s demands. Unfortunately, the company is not old enough to have last year data for December, so we can not look back at past demands to prepare forecast for December’s demands. This project would aim to make an automated forecasting model for hourly demands that would be evaluated on the next 7 days (Sunday, December 3rd 2017 to Monday, December 9th 2017).

Logistic Regression Modeling and K-NN to predict heart disease in patients with 13 variables.