Skip to content

ARPM (Advanced Risk and Portfolio Management) Project

Jump to bottom Edit New page
Erol Biceroglu edited this page Mar 21, 2019 · 8 revisions

Background

ARPM is an education firm founded in 2010 by Attilio Meucci. ARPM teaches the ARPM Bootcamp, a 6-day, 500+ people onsite (NYC)/online course and networking experience which consolidates portfolio managers’ and risk managers’ expertise into a rigorous quantitative framework. Over the past years, ARPM has built the ARPM Lab, an online e-learning platform that contains theory, case studies, simulation clips, toy examples, summary slides, video lectures, code (Python/MATLAB), documentation, exercises, and more.

The goal for this project is to convert the Python functions currently in the ARPM Lab into R, with particular attention to two parts:

  • The “Checklist” (10-step approach for integrated quantitative risk and portfolio management)
  • Factor Models and Learning (Multivariate statistics and machine learning for finance)

Students engaged in this project will obtain a deep understanding of i) Data science for finance ii) Quantitative risk management iii) Quantitative portfolio management across asset management, insurance, and banking.

As part of this project, students will execute a copyright assignment granting copyright to ARPM.

Related work

This project takes its inspiration from previous GSoC projects in 2012, 2013 and 2014, as well as the new interactive ARPM Lab.

The development version of the functions backing the ARPM Lab scripts is available at https://gitlab.com/arpm-lab/arpm_r.

We envision the following steps for this project:

  • Familiarization with the theory of a topic
  • Work with the GSoC mentor(s) to write core script functions, which will then be used on the ARPM Lab
  • Complete minimal documentation

The project will be developed with https://www.rstudio.com/ and stored on https://gitlab.com. In order to efficiently manage the development of the package, the various tasks and deadlines will be managed via https://asana.com/.

Mentors

Erol Biceroglu, Prof. Brian Peterson, Prof. Dr. David Ardia, and Attilio Meucci.

Tests

The official test for this project can be found at this link.

In addition to the test above, applicants should demonstrate that they have:

  • A very good working knowledge of programming in R.
  • A very good working knowledge of Roxygen for the documentation.
  • Familiarities with the construction of R packages.
  • Good coding standards (Google’s C++ and R style guide).
  • Good knowledge of Meucci's methods
  • Experience with multivariate statistics
  • Experience with git, GitHub/GitLab
  • code for the ARPM package will be released under the Affero Gnu Public License

Solutions of tests

Students, please post a link to your test results here.

References

ARPM Lab

Add a custom footer
Add a custom sidebar
Clone this wiki locally