{"paper_id":"2508.10300","title":"Optimal Capital Deployment Under Stochastic Deal Arrivals: A Continuous-Time ADP Approach","authors":["Kunal Menda","Raphael S Benarrosh"],"paper_date":"2025-08-14","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2508.10300v1","page_url":"https://thequant.space/flowcharts/optimal-capital-deployment-under-stochastic-deal-arrivals-a/","scores":{"empirical_rigor":7.2,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper formulates capital deployment under stochastic deal arrivals as a continuous‑time Markov decision process and solves it numerically with an approximate dynamic programming approach that uses quasi‑Monte Carlo sampling on a discretized capital grid.","quote":"This work formulates the problem of capital deployment under stochastic deal arrivals as a continuous-time Markov decision process (CTMDP) and solves it numerically via an approximate dynamic programming (ADP) approach. Our approach uses quasi-Monte Carlo (QMC) sampling to efficiently approximate the continuous-time Bellman equation for the value function over a discretized capital grid.","summary":"Suppose you are a fund manager with $100 million to deploy and two years to invest it. A deal comes across your desk that looks appealing but costs $50 million – half of your available capital. Should you take it, or wait for something better? The decision hinges on the trade-off between current…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The fund starts with $100 million of capital and has a two‑year investment horizon.","type":"model","stated":"explicit","quote":"Suppose you are a fund manager with \\$100 million to deploy and two years to invest it.","support":"full"},{"assumption":"Deal arrivals follow a non‑homogeneous Poisson process.","type":"model","stated":"explicit","quote":"We model deal economics using correlated lognormal distributions for multiples on invested capital (MOIC) and deal sizes, and model arrivals as a nonhomogeneous Poisson process (NHPP). We model the capital deployment problem as a continuous-time Markov decision process (CTMDP) [4] governed by the continuous-time Bellman equation [5], with arrivals following a nonhomogeneous Poisson process (NHPP) [6] and deal","support":"full"},{"assumption":"Deal multiples on invested capital (MOIC) and deal sizes are jointly lognormally distributed with a specified correlation.","type":"statistical","stated":"explicit","quote":"We model deal economics using correlated lognormal distributions for multiples on invested capital (MOIC) and deal sizes, and model arrivals as a nonhomogeneous Poisson process (NHPP). We model the capital deployment problem as a continuous-time Markov decision process (CTMDP) [4] governed by the continuous-time Bellman equation [5], with arrivals following a nonhomogeneous Poisson process (NHPP) [6] and deal","support":"full"},{"assumption":"A hurdle IRR of 15 % is used as the minimum acceptable return for investment decisions.","type":"model","stated":"explicit","quote":"We set the hurdle IRR rhurdle = 15%.","support":"full"},{"assumption":"Each deal’s cash‑flow is returned five years after investment.","type":"model","stated":"explicit","quote":"We assume that each deal returns capital five years after investment.","support":"full"},{"assumption":"In the experimental validation, deal arrivals are modeled as a homogeneous Poisson process with an average rate of 12 deals per year.","type":"model","stated":"explicit","quote":"Deal arrivals follow a Poisson process with an average rate of 12.0 deals per year (assumed to be homogeneous for simplicity).","support":"partial"}]},"datasets":{"status":"available","items":[{"name":"Synthetic deal arrivals and characteristics","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Deal arrivals follow a Poisson process with an average rate of 12.0 deals per year (assumed to be homogeneous for simplicity). Calculating the internal rate of return (IRR) r = M 1/5 −1, we model deal characteristics using correlated lognormal distributions: deal sizes have mean $50 M and standard deviation $25 M, and deal IRR has mean 20% and standard deviation 2.5%.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"none_found","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"none","rule":"R0b","candidates":{"front_matter":"unclear","evidence_card":"no","evidence_card_quoted":false},"meaning":"no cost treatment was found in the passages the extractor read; that is not evidence that costs are not modeled"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"In simulation, the ADP‑derived acceptance policy yields a mean portfolio IRR of 23.6 %, outperforming the baseline policy by 2.5 %.","kind":"performance","quote":"The ADP policy achieves a mean IRR of 23.6%, outper-forming the baseline policy by 2.5%.","support":"full"},{"finding":"The ADP policy consistently outperforms a baseline that accepts any affordable deal exceeding a fixed hurdle rate in simulated experiments.","kind":"performance","quote":"We show in simulation that this policy outperforms a baseline that accepts any affordable deal exceeding a fixed hurdle rate. We show in simulation that this policy delivers a higher portfolio return than a baseline that accepts any affordable deal exceeding a fixed hurdle rate.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":6,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T19:48:32Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}