DPhi Machine Learning Bootcamp
Repository for the assignments of the DPhi Machine Learning bootcamp
The exploratory analysis, the steps took to solve this challenge and possible future actions are found in the assignment 1 notebook inside the assignment 1 folder.
The links to the training and test data can be found inside the notebook as well.
Travel insurance is a type of insurance that covers the costs and losses associated with traveling. It is useful protection for those traveling domestically or abroad.
Many companies selling tickets or travel packages, give consumers the option to purchase travel insurance, also known as travelers insurance. Some travel policies cover damage to personal property, rented equipment, such as rental cars, or even the cost of paying a ransom.
Imagine you are working as a data scientist in an insurance company in the USA. The company has collected the data of earlier travel insurance buyers. In this season of vacation, the company wants to know which person will claim their travel insurance and who will not. The company has chosen you to apply your Machine Learning knowledge and provide them with a model that achieves this vision.
You are responsible for building a machine learning model for the insurance company to predict if the insurance buyer will claim their travel insurance or not.
Submissions are evaluated using F1 Score.
How do we do it?
Once we release the data, anyone can download it, build a model, and make a submission. We give competitors a set of data (training data) with both the independent and dependent variables.
We also release another set of data (test dataset) with just the independent variables, and we hide the dependent variable that corresponds with this set. You submit the predicted values of the dependent variable for this set and we compare it against the actual values.
The predictions are evaluated based on the evaluation metric defined in the datathon.
Heart disease describes a range of conditions that affect your heart. With growing stress, the number of cases of heart diseases are increasing rapidly.
According to the World Health Organisation(WHO), Cardiovascular diseases (CVDs) are the number 1 cause of death globally, taking an estimated 17.9 million lives each year. 17.9 million people die each year from CVDs, an estimated 31% of all deaths worldwide.
The doctors of Health Hospital in Zastra wish to incorporate Data Science into their workings. Seeing the rising cases of heart diseases, they are specially interested in predicting the presence of heart disease in a person using some existing data. The first step they are taking towards it is to conduct a Datathon to find the best Machine Learning Engineers available out there.
The idea behind this ML project is to build an ML model to determine if heart disease is present or not i.e if the target is 1 or 0.
Submissions are evaluated using F1 Score.
How do we do it?
Once we release the data, anyone can download it, build a model, and make a submission. We give competitors a set of data (training data) with both the independent and dependent variables.
We also release another set of data (test dataset) with just the independent variables, and we hide the dependent variable that corresponds with this set. You submit the predicted values of the dependent variable for this set and we compare it against the actual values.
The predictions are evaluated based on the evaluation metric defined in the datathon.
A loan application is used by borrowers to apply for a loan. Through the loan application, borrowers reveal key details about their finances to the lender. The loan application is crucial to determining whether the lender will grant the request for funds or credit.
The director of SZE bank identified that going through the loan applications to filter the people who can be granted loans or need to be rejected is a tedious and time-consuming process. He wants to automate it and increase his bank’s efficiency. After talking around a bit, your name pops up as one of the few data scientists who can make this possible within a limited time. Will you help the director out?
The idea behind this ML project is to build an ML model and web application that the bank can use to classify if a user can be granted a loan or not.
Submissions are evaluated using F1 Score.
How do we do it?
Once we release the data, anyone can download it, build a model, and make a submission. We give competitors a set of data (training data) with both the independent and dependent variables.
We also release another set of data (test dataset) with just the independent variables, and we hide the dependent variable that corresponds with this set. You submit the predicted values of the dependent variable for this set and we compare it against the actual values.
The predictions are evaluated based on the evaluation metric defined in the datathon.