Topic outline

  • Machine Learning in Financial Engineering


    This course will be taught again in spring 2024. Welcome!


    -


    IMPORTANT: prerequisite for the course: 

    TU-E2210 Financial Engineering I + Python/R

    OR 

    basics in finance + Python/R.

    We will use Python during the course, and the algorithms will be given only in Python. A student who is very strong in R can use it. The course will be calibrated to the level of the students of Financial Engineering I. 

    Topics to be considered: 

    • Data analysis: Financial data structures, labeling, data weights
    • Modeling: supervised and unsupervised methods (regression, PCA, clustering, random forest, Bayesian methods)
    • Cross-validation: LOOCV, K-Fold
    • Backtesting
    • Natural Language Processing

    Passing the course: 

    The lectures will be held in a hybrid form in via Zoom on Wednesdays at 14.15-16.00
    The exercises will be done individually in Jupyter.

    A 3 credit version, a 5 credit version or a 6 credit version of the course are available. 

    3 credit version: 
    Weekly exercises (reflection on the lectures and analysis/solutions of Python exercises done in Jupyter)
    grading: passed/failed

    5 credit version: 
    Weekly exercises (reflection on the lectures and analysis/solutions of Python exercises done in Jupyter)
    Assignment (done in group or individually)
    grading: passed/failed

    6 credit version: 
    same as 5 credit version + essay on a scientific article
    grading: passed/failed

    This course can be included in the minor Financial Engineering. Click here for further information.


    For additional information, please contact the FE III team: Ruth Kaila, ruth.kailaATaalto.fi or Eljas Toepfer, eljas.toepferATaalto.fi.  


    • Announcements Forum
    • Assignment, 5 credit and 6 credit versions, dl 19.4. Folder