Paper: arXiv 2307.05048

Authors: Jaydip Sen, Subhasis Dasgupta

Abstract

Portfolio optimization has been an area that has attracted considerable attention from the financial research community. Designing a profitable portfolio is a challenging task involving precise forecasting of future stock returns and risks. This chapter presents a comparative study of three portfolio design approaches, the mean-variance portfolio (MVP), hierarchical risk parity (HRP)-based portfolio, and autoencoder-based portfolio. These three approaches to portfolio design are applied to the historical prices of stocks chosen from ten thematic sectors listed on the National Stock Exchange (NSE) of India. The portfolios are designed using the stock price data from January 1, 2018, to December 31, 2021, and their performances are tested on the out-of-sample data from January 1, 2022, to December 31, 2022. Extensive results are analyzed on the performance of the portfolios. It is observed that the performance of the MVP portfolio is the best on the out-of-sample data for the risk-adjusted returns. However, the autoencoder portfolios outperformed their counterparts on annual returns.

Complexity vs Empirical Score

  • Math Complexity: 4.5/10
  • Empirical Rigor: 6.0/10 (capped from 7.5: transaction costs not modelled; see penalty flags)
  • Quadrant: Street Traders — empirical and applied, lower math complexity (effective empirical rigor capped from 7.5)

Why this score: The paper applies standard portfolio optimization techniques (MVP, HRP, autoencoders) with a clear, real-world out-of-sample backtest using specific NSE stock data over defined time periods. While the math is foundational (covariance matrices, Sharpe ratio) and not highly novel or dense, the empirical setup is detailed, data-driven, and implementation-focused, aiming for practical investment guidance.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Comparative Study of<br>Portfolio Optimization Models"] --> B{"Data Collection"}
  
  B --> C["Input: NSE Stocks<br>Jan 2018 - Dec 2021<br>(Training Period)"]
  
  C --> D["Model Application"]
  
  subgraph D ["Computational Processes"]
      D1["Mean-Variance Portfolio MVP"]
      D2["Hierarchical Risk Parity HRP"]
      D3["Autoencoder-based Portfolio"]
  end
  
  D --> E["Out-of-Sample Testing<br>Jan 2022 - Dec 2022"]
  
  E --> F{"Performance Analysis"}
  
  F --> G["Key Findings<br>MVP: Best Risk-Adjusted Returns<br>Autoencoder: Best Annual Returns"]

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 comparative study of three portfolio design approaches—mean‑variance, hierarchical risk parity, and autoencoder‑based—applied to NSE stocks.

Source sentence
This chapter presents a comparative study of three portfolio design approaches, the mean-variance portfolio (MVP), hierarchical risk parity (HRP)-based portfolio, and autoencoder-based portfolio.

Assumes 2

  • There are 250 working days in a year for converting daily volatility to annual volatility. statistical
    Source sentence
    The daily volatility, on multiplication by a factor of the square root of 250, yields the value of the annual volatility. Here, there is a standard assumption of 250 working days in a year for a stock market.
  • Stocks are selected as the ten with maximum free‑float market capitalization in each sector. data
    Source sentence
    The portfolios are designed based on the historical prices of the ten stocks from the ten sectors which have the maximum free‑float market capitalization.

Data

Backtest sample: 2018-01 – 2022-12 · National Stock Exchange (NSE) of India stocks · equities · daily

  • Historical stock prices of NSE thematic sectors · National Stock Exchange of India market-prices public
    2018-01-01 to 2022-12-31 · Ten thematic sectors, ten stocks per sector
    Source sentence
    These three approaches to portfolio design are applied to the historical prices of stocks chosen from ten thematic sectors listed on the National Stock Exchange (NSE) of India. The portfolios are designed using the stock price data from January 1, 2018, to December 31, 2021, and their performances are tested on the out

Recognised sources: Yahoo Finance

Costs

Not modeled A trading or execution result is reported without costs.

Finds 3

  • The MVP portfolio achieved the best risk‑adjusted returns (highest Sharpe ratios) on out‑of‑sample data for most sectors. performance
    Source sentence
    It is observed that the MVP portfolios have yielded the highest risk‑adjusted returns and Sharpe ratios for the majority of the sectors on the out‑of‑sample data.
  • Autoencoder‑based portfolios delivered the highest annual returns for most sectors. performance
    Source sentence
    However, autoencoder‑based portfolios are found to have yielded the maximum annual returns for most of the sectors studied in this work.
  • On training data, the ENC portfolio produced the highest returns for five sectors, while MVP produced the highest Sharpe ratios for six sectors and the lowest volatility for all ten sectors. performance
    Source sentence
    It is observed that the ENC portfolio produced the highest returns for five sectors, while the highest values of the Sharpe ratio were yielded by the MVP portfolio for six sectors. However, the MVP portfolio produced the minimum values of volatility for all ten sectors.

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.

Cited by 1 paper in the archive (1 by independent authors)

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.