Paper: arXiv 2412.03305
Authors: A. V. Kuliga, I. N. Shnurnikov
Abstract
An investment portfolio consists of \(n\) algorithmic trading strategies, which generate vectors of positions in trading assets. Sign opposite trades (buy/sell) cross each other as strategies are combined in a portfolio. Then portfolio turnover becomes a non linear function of strategies turnover. It rises a problem of effective (quick and precise) portfolio turnover estimation. Kakushadze and Liew (2014) shows how to estimate turnover via covariance matrix of returns. We build a mathematical model for such estimations; prove a theorem which gives a necessary condition for model applicability; suggest new turnover estimations; check numerically the preciseness of turnover estimations for algorithmic strategies on USA equity market.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 8.0/10
- Quadrant: Holy Grail — high math complexity, high empirical rigor
Why this score: The paper features advanced mathematical modeling, including theorems and eigenvalue-based derivations for turnover estimation, warranting a high math complexity score. It is strongly grounded in empirical finance, with a dedicated section for backtesting on USA equity markets, quantitative validation of estimations, and practical considerations like trade crossing and transaction costs, indicating high empirical rigor.
Research Flowchart
flowchart TD A["Research Goal<br>Effective Portfolio Turnover Estimation"] --> B["Methodology<br>Covariance Matrix Model"] B --> C["Data Input<br>USA Equity Market Algorithmic Strategies"] C --> D["Computational Process<br>Model Theorem & Numerical Simulation"] D --> E["Outcome 1<br>Proof of Necessary Condition"] D --> F["Outcome 2<br>Novel Turnover Estimations"] D --> G["Outcome 3<br>Verified Estimation Preciseness"]
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 builds a mathematical model for turnover estimation, proves a necessary condition theorem, and suggests new turnover estimations.
Source sentence
We build a mathematical model for such estimations; prove a theorem which gives a necessary condition for model applicability; suggest new turnover estimations
Assumes 6
- The components of the alpha vector α are linearly independent with a constant, ensuring non‑degeneracy of the covariance matrix. model
Source sentence
The non-degeneracy of the matrix B (and the existence of B−1/2) follows from the fact that the components of α are linearly independent with a constant.
- For the proof it is assumed that the covariance matrix C(α) can be taken as the identity matrix. model
Source sentence
By lemma 1 we may assume that the matrix C(α) is identity.
- Alpha positions are updated at the beginning of each trading day, giving the whole day for execution. execution
Source sentence
These alphas calculate position vectors by the beginning of the trading day, so the execution has the whole day to achieve the required positions.
- Daily open, high, low, close, volume data from Yahoo Finance for ~1400 liquid US stocks are used. data
Source sentence
We use daily data open, high, low, close, volume from Yahoo Finance for approximately 1400 most liquid USA stocks.
Show 2 more
- In‑sample period is 2010‑2014 and out‑of‑sample testing period is 02.01.2018 – 14.06.2024. data
Source sentence
For alpha research we use 2010 — 2014 as in‑sample, and use 02.01.2018 – 14.06.2024 for testing as out‑of‑sample.
- The function f used in the theoretical development is absolutely homogeneous and not identically zero. model
Source sentence
Since f̸ ≡0 there exists β1 ∈V (α) such that f(β1)̸ = 0 and Dβ1 = 1.
Data
- Yahoo Finance daily data market-prices public
Source sentence
We use daily data open, high, low, close, volume from Yahoo Finance for approximately 1400 most liquid USA stocks.
Costs
Not applicable
Finds 3
- Turnover estimations are more precise when the ratios τi/std_i differ only slightly across alphas; in that case the proposed estimations (2.4) perform best. theoretical
Source sentence
Estimations become more precise in the case when the ratios τi/std i differ a little for alphas of portfolio.
- If the τi/std_i ratios differ significantly, the earlier estimations (1.1) or (1.2) are preferred. theoretical
Source sentence
Else, if ratio τi/std i differ significantly, then estimations (1.1) or (1.2) are preferred.
- Theorem 1 provides a tool to analyze models of absolutely homogeneous portfolio functions that depend on the covariance matrix of returns. theoretical
Source sentence
The theorem 1 could help to analyse the models of other absolutely homogeneous functions of portfolio, which depend on covariance matrix of returns.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 13 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.