Reinforcement learning; Private Equity; Control system
Abstract :
[en] Recommitments are essential for limited partner investors to maintain a target exposure to private equity. However, recommitting to new funds is irrevocable and expose investors to cashflow uncertainty and illiquidity. Maintaining a specific target allocation is therefore a tedious and critical task. Unfortunately, recommitment strategies are still manually designed and few works in the literature have endeavored to develop a recommitment system balancing opportunity cost and risk of default. Due to its strong similarities to a control system, we propose to “learn how to recommit” with Reinforcement Learning (RL) and, more specifically, using Proximal Policy Optimisation (PPO). To the best of our knowledge, this is the first attempt a RL algorithm is applied to private equity with the aim to solve the recommitment problematic. After training the RL model on simulated portfolios, the resulting recommitment policy is compared to state-of-the-art strategies. Numerical results suggest that the trained policy can achieve high target allocation while bounding the risk of being overinvested.
Research center :
ULHPC - University of Luxembourg: High Performance Computing
Disciplines :
Computer science
Author, co-author :
Kieffer, Emmanuel ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Pinel, Frederic ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Meyer, Thomas; SimCorp Luxembourg SA, Luxembourg
Gloukoviezoff, Georges; European Investment Bank, Luxembourg
Lucius, Hakan; European Investment Bank, Luxembourg
Bouvry, Pascal ; University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
External co-authors :
no
Language :
English
Title :
Proximal Policy Optimisation for a Private Equity Recommitment System
Publication date :
2021
Event name :
BNAIC/BeneLearn 2021 AI & ML conference
Event place :
Luxembourg
Event date :
from 10-11-2021 to 12-11-2021
Audience :
International
Main work title :
Springer CCIS series
Peer reviewed :
Peer reviewed
Focus Area :
Computational Sciences
Name of the research project :
Toward A.I. Recommitment Strategies for ESG integration in Private Equity
Achiam, J.: Spinning Up in Deep Reinforcement Learning (2018)
Agarap, A.F.: Deep learning using rectified linear units (relu) http://arxiv.org/abs/1803.08375, arxiv:1803.08375Comment (2018)
Arnold, T.R., Ling, D.C., Naranjo, A.: Waiting to be called: the impact of manager discretion and dry powder on private equity real estate returns. J. Portfolio Manag. 43(6), 23–43 (2017)
Cardie, J.H., Cattanach, K.A., Kelly, M.F.: How large should your commitment to private equity really be? J. Wealth Manag. 3(2), 39–45 (2000)
Gabriel, E., et al.: Open MPI: Goals, concept, and design of a next generation MPI implementation. In: Proceedings of 11th European PVM/MPI Users’ Group Meeting, pp. 97–104. Budapest, Hungary(2004)
Hasselt, H.v., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pp. 2094–2100. AAAI 2016, AAAI Press (2016)
Lerner, J., Schoar, A.: The illiquidity puzzle: theory and evidence from private equity. J. Financ. Econ. 72(1), 3–40 (2004)
de Malherbe, E.: Modeling private equity funds and private equity collateralised fund obligations. Int. J. Theor. Appl. Financ. 07, 193–230 (2004)
Meyer, T.: Hidden in plain sight-the impact of undrawn commitments. J. Altern. Investments 23(2), 94–110 (2020)
Mnih, V., et al.: Playing atari with deep reinforcement learning http://arxiv.org/abs/1312.5602, arxiv:1312.5602Comment (2013)
Nevins, D., Conner, A., McIntire, G.: A portfolio management approach to determining private equity commitments. J. Altern. Investments 6(4), 32–46 (2004)
Oberli, A.: Private equity asset allocation: how to recommit? J. Private Equity 18(2), 9–22 (2015)
Schulman, J., Moritz, P., Levine, S., Jordan, M., Abbeel, P.: High-dimensional continuous control using generalized advantage estimation. In: Proceedings of the International Conference on Learning Representations (ICLR) (2016)
Takahashi, D., Alexander, S.: Illiquid alternative asset fund modeling. J. Portfolio Manag. 28(2), 90–100 (2002)
Varrette, S., Bouvry, P., Cartiaux, H., Georgatos, F.: Management of an academic HPC cluster: the UL experience. In: Proceedings of the 2014 International Conference on High Performance Computing and Simulation (HPCS 2014), pp. 959–967. IEEE, Bologna, Italy (2014)
de Zwart, G., Frieser, B., van Dijk, D.: Private equity recommitment strategies for institutional investors. Financ. Anal. J. 68(3), 81–99 (2012)