Paper: arXiv 2405.12991

Authors: Mohammed Perves

Abstract

Computing cost of equity for private corporations and performing comparable company analysis (comps) for both public and private corporations is an integral but tedious and time-consuming task, with important applications spanning the finance world, from valuations to internal planning. Performing comps traditionally often times include high ambiguity and subjectivity, leading to unreliability and inconsistency. In this paper, I will present a systematic and faster approach to compute cost of equity for private corporations and perform comps for both public and private corporations using spectral and agglomerative clustering. This leads to a reduction in the time required to perform comps by orders of magnitude and entire process being more consistent and reliable.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 2.0/10
  • Quadrant: Philosophers — conceptual discussion, lower math and empirical scores

Why this score: The paper relies on established financial formulas (CAPM, WACC) and clustering algorithms (spectral, agglomerative) but presents them descriptively without complex derivations or novel mathematical advancement. Empirically, it outlines a theoretical methodology using publicly available tools but lacks any reported backtests, dataset descriptions, or statistical validation of results.

Research Flowchart

  flowchart TD
  A["Research Goal: Systematic Comps &<br>Cost of Equity for Private Firms"] --> B["Data: Financial &<br>Market Inputs"]
  B --> C["Methodology: Spectral &<br>Agglomerative Clustering"]
  C --> D["Computation: Cluster-based<br>Cost of Equity Calculation"]
  D --> E{"Key Outcomes"}
  E --> F["Reduced Time by<br>Orders of Magnitude"]
  E --> G["Enhanced Consistency<br>& Reliability"]

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 proposes a systematic and faster approach to compute cost of equity for private corporations and perform comparable company analysis using spectral and agglomerative clustering.

Source sentence
In this paper, I will present a systematic and faster approach to compute cost of equity for private corporations and perform comps for both public and private corporations using spectral and agglomerative clustering.

Assumes 3

  • Private corporations do not have a beta or pay dividends, so traditional CAPM or dividend models cannot be applied directly. model
    Source sentence
    To compute the WACC for private corporations we cannot use these methods directly because private corporations don’t have a Beta or pay out dividends.
  • Document vectors are created using Doc2Vec combined with TF‑IDF. execution
    Source sentence
    I will be using Doc2Vec in combination with TF-IDF in this paper.
  • The dataset consists of the 487 unique stocks listed on the S&P 500 index. data
    Source sentence
    I will be using the 487 unique stocks listed on the S&P 500 index.

Data

  • S&P 500 Wikipedia pages · Wikipedia text-news public
    S&P 500 constituents
    Source sentence
    I will be using the Wikipedia pages for each of the stocks to perform document clustering.

Recognised sources: WRDS

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • The clustering‑based approach reduces the time required to perform comparable company analysis by orders of magnitude and makes the process more consistent and reliable. performance
    Source sentence
    This leads to a reduction in the time required to perform comps by orders of magnitude and entire process being more consistent and reliable.
  • Clustering models can successfully identify peers for companies, enabling systematic creation of comparable company analysis for both public and private firms. theoretical
    Source sentence
    To conclude, I think clustering models can successfully identify peers for companies, which can be used to systematically create comparable company analysis for both public and private companies, reducing the time required to search for peers manually.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 8 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

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