Paper: arXiv 2402.15588

Authors: Vuko Vukcevic, Robert Keser

Abstract

The paper provides a mathematical model and a tool for the focused investing strategy as advocated by Buffett, Munger, and others from this investment community. The approach presented here assumes that the investor’s role is to think about probabilities of different outcomes for a set of businesses. Based on these assumptions, the tool calculates the optimal allocation of capital for each of the investment candidates. The model is based on a generalized Kelly Criterion with options to provide constraints that ensure: no shorting, limited use of leverage, providing a maximum limit to the risk of permanent loss of capital, and maximum individual allocation. The software is applied to an example portfolio from which certain observations about excessive diversification are obtained. In addition, the software is made available for public use.

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 2.0/10
  • Quadrant: Lab Rats — high math complexity, limited empirical testing

Why this score: The paper presents a generalized Kelly Criterion with a non-linear system of equations derived from probability-weighted scenarios, showing significant mathematical density. However, it lacks any backtesting, datasets, or statistical metrics, and the empirical application is limited to a single example portfolio without performance data.

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Focused Portfolio Sizing"] --> B{"Key Methodology"}
  B --> C["Data/Inputs:<br>Est. Return &<br>Probability of Outcomes"]
  C --> D["Computational Process:<br>Generalized Kelly<br>with Constraints"]
  D --> E["Outputs:<br>Optimal Capital<br>Allocation"]
  E --> F["Key Findings:<br>Excessive Diversification<br>Reduced Risk"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper provides a mathematical model and a tool for the focused investing strategy, based on a generalized Kelly Criterion with constraints such as no shorting and limited leverage.

Source sentence
The paper provides a mathematical model and a tool for the focused investing strategy as advocated by Buffett, Munger, and others from this investment community. The model is based on a generalized Kelly Criterion with options to provide constraints that ensure: no shorting, limited use of leverage, providing a maximum limit to the risk of permanent loss of capital, and maximum individual allocation.

Assumes 3

  • The number of bets is assumed to be very high (tends to infinity). model
    Source sentence
    During the mathematical derivation presented in section 3, an assumption is made that the number of bets is very high (tends to infinity).
  • If the inputs to the mathematical model are unrealistic, the results will be unrealistic as well. other
    Source sentence
    Therefore, the reader should always keep in mind that if the inputs to the mathematical model are unrealistic, the results will be unrealistic as well.
  • The framework remains valid as long as the input probabilities are conservatively estimated. model
    Source sentence
    Therefore, as long as the input probabilities are conservatively estimated, the framework should still be valid.

Data

No dataset named in the text.

Costs

Not applicable The paper reports no trading or execution result.

Finds 5

  • Applying the software to an example portfolio yields observations about excessive diversification. theoretical
    Source sentence
    The software is applied to an example portfolio from which certain observations about excessive diversification are obtained.
  • The numerical procedure iteratively solves a constrained non‑linear system to obtain optimal allocation fractions. theoretical
    Source sentence
    4.3 Notes on the Numerical Procedure The numerical procedure starts by assuming the uniform allocation across all companies, i.e. fj = f = 1 Nc . Based on the f o j in the current iteration, the linear system in equation (10) is solved to find the new solution f n j .
  • Among viable solutions, the chosen allocation maximizes the expected value of the portfolio while favoring the most diversified solutions. theoretical
    Source sentence
    In this work, we take a pragmatic approach and simply choose the solution that maximizes the expected value of the portfolio out of a set of most diversified solutions, i.e. the solutions with the highest number of non–zero allocations.
  • A basic validation test with five candidate companies demonstrates the model’s behavior under uniform scenario assumptions. theoretical
    Source sentence
    5 Basic Validation Tests In order to validate the numerical model, a basic example of five candidate com-panies is considered, where each candidate has the same set of scenarios (proba-bilities and intrinsic values) and the same market cap.
  • The software is freely available as a Rust crate for public use. other
    Source sentence
    In addition, the software is made available for public use. 11 8 Access to the Software The software is freely available as a Rust crate at https://crates.io/crates/charlie, and its source code is hosted on GitLab at https://gitlab.com/in-silico-public/charlie.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 18 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

https://gitlab.com/in-silico-public/charlie — the authors' own repository

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (19)

  1. Thinking, Fast and Slow (2011)
  2. Influence: The Psychology of Persuasion (2006)
  3. Poor Charlie’s Almanack: The Wit and Wisdom of Charles T. Munger (2005)
  4. The Intelligent Investor (2003)
  5. A New Interpretation of Information Rate (1956)
  6. Generalized framework for applying the Kelly criterion to stock markets (2018)
  7. Actuarial Life Table (2023)
  8. Maximizing Portfolio Predictability with Machine Learning — → 2311.01985
and 11 more
  1. Kelly Criterion: From a Simple Random Walk To L' e vy Processes (2020) — link
  2. On the Benefit of Nonlinear Control for Robust Logarithmic Growth:Coin Flipping Games as a Demonstration Case — → 2303.10417
  3. Sports Betting: An Application of Neural Networks and Modern Portfolio Theory to the English Premier League — → 2307.13807
  4. James, N. and Menzies, M. (2023) — link
  5. Sparse spanning portfolios and under-diversification with second-order stochastic dominance — → 2402.01951
  6. A quantum double-or-nothing game: The Kelly Criterion for Spins — → 2308.01305
  7. Gambling the World Away: Myopic Investors — → 2302.13994
  8. Berkshire Hathaway Shareholder Letters (2023)
  9. Nomad Investment Partnership Letters to Investors (2021)
  10. Li Lu’s Lecture at Professor Greenwald’s 2006 Class. (2023)
  11. What I Learned About Investing from Darwin (2023)

6 of 19 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.