Loading...
hidden

View Mobile version

Meta navigation

Startseite – Hochschule Luzern

Language selection and important links

  • Contents
  • Contact
  • Login
  • De
  • En
Search

Main navigation

School navigation

  • Engineering and Architecture
  • Business
  • Computer Science
  • Social Work
  • Design, Film and Art​
  • Music
  • Health Sciences

Sub-navigation

  • Degree Programmes
  • Continuing Education
  • Research
  • International
  • Campus
  • About us
  • News

Sub-navigation

Breadcrumbs

  1. Research Research
  2. Research and Services Projects Research and Services Projects
  3. Asset Allocation through Reinforcement Learning for Swiss Pension Funds Asset Allocation through Reinforcement Learning for Swiss Pension Funds

Asset Allocation through Reinforcement Learning for Swiss Pension Funds

Deep reinforcement learning is employed to improve the asset allocations of Swiss pension funds.

Brief information

School:

Business

Status:

Ongoing

Period:

01.12.2022 - 31.08.2025

Overview

This project aims to develop two new machine learning-based strategies for dynamic asset allocation, to hopefully help pension funds avoid large drawdowns. Broadly, the first strategy is based on a funds-of-funds approach, and the second on a single-stock approach. Between them, they combine a variety of innovative aspects. Based on a deep reinforcement learning paradigm, they 1. Solve the investment problem, which is traditionally approached in two steps (estimation, then optimization), in a single step. 2. Introduce a new objective function replacing the commonly used Sharpe ratio to induce (approximate) time separability. 3. Exploit the resulting time separability of the investment problem to significantly reduce training and inference time. 4. Employ a novel differentiable approximation to the maximum drawdown metric, to facilitate penalizing downside risk. 5. Augment the state of the learning problem with factor portfolio data to incorporate the factor investing paradigm. 6. Allow for sparse portfolios (stock picking) by introducing L1 penalties.

hidden

Facts

Type of project

Forschung

Internal organisations involved
  • CC Financial Services (IFZ FSM)
Funding
  • Innosuisse - HSLU als Hauptforschungspartnerin (Main Research Partner)
hidden

Persons involved: internal

Project manager
  • Simon Broda
Project Co-Head
  • Fabio Sigrist

Publications

  • Report/working paper (1)

    • Broda, Simon & Walker, Patrick (2025). Dynamic Asset Allocation with Reinforcement Learning (Bericht).

Brief information

School:

Business

Status:

Ongoing

Period:

12/01/2022 - 08/31/2025

Project Head

Dr. Simon Broda

Lecturer

+41 41 757 67 97

Show email

Project Co-Head

Prof. Dr. Fabio Sigrist

Lecturer

+41 41 757 67 61

Show email

Footer(s)

FH Zentralschweiz

Social media links

  •  Instagram
  •  LinkedIn
  •  TikTok
  •  Facebook
  •  YouTube
  •  Flickr

Contact

Logo Lucerne University of Applied Sciences and Arts

Lucerne University of Applied Sciences and Arts


Werftestrasse 4
6002 Luzern

+41 41 228 42 42

info@hslu.ch

Direct entry

  • Bachelor’s Degree
  • Master’s Degree
  • Prospective Students (Continuing & Executive Programmes)
  • For Students
  • For Employees

Quick link

  • People Finder
  • University Buildings & Campus Locations
  • News
  • Libraries
  • Events
  • Media Relations
  • Jobs and Careers
  • Home
  • Hiring Rooms

Static links

  • Newsletter
  • Data protection notice
  • Publishing Acknowledgements
Logo Swissuniversities

QrCode

QrCode