Delivery of the case solutions:

Summer school on modelling & complex systems

Delivery of the case solutions:

  1. Before the deadline (13:00,11.07.2021) you should deliver the solutions here…
  2. The solution should consist of at least the following:
    • Code / workflow files which could be run on some of the required software for the summer school.
    • In the code or in additional files there should be complete explanations, visualisations and data anaysis results to solve the case.
    • List of authors.
  3. There could be more than one solution per team.
  4. Each team will be given about 15-20 minutes to present their solutions followed by Q&A session.

The cases for this year’s Summer school are:

The cases for this year’s Summer school are:

  1. The A.I. crypto trader - Make a prediction model of the major cryptocurrencies’ prices and an autonomous A.I. decision-maker for trading/investing
    Crypto case text…
    Crypto case data (csv or sql)…

Team solutions here…, video

  1. World Development indicators (panel data) - Discover factors for contry economic development and make recommendations
    Download data…

Team solutions here…, video

  1. Product Recommendation - Can you pair products with people?
    Download the data and read the case…

Team solutions here…, video

  1. The 04 April Parlamentary Elections - discover signs of false play and /or other peculiar tendencies in the latest parlamentary elections results (open case).
    Data (read the README file)…

A case for homework exercise

  1. Lending club - find a suitable customer for a loan. This dataset contains the full LendingClub data from 2007 to 2018. There are separate files for accepted and rejected loans. The accepted loans also include the FICO scores, which can only be downloaded when you are signed in to LendingClub and download the data.

Task 1: Predict if a future customer will pay back the loan. Make a model to assess whether or not a new customer is likely to pay back the loan. You can use several different machine learning models.

Task 2: Classify Loans by Grade. Categorize accepted loans into one of the seven loan grades. In the accepted loans data, we have a column called “grade.” It takes values from A-G (A is the best, G is the worst). The task is to build a classifier that, given some other features, can accurately categorize a loan by grade.

Accepted loans data
Rejected loans data