Scholarlink

<p>To identify the assets contributing to downward market trend, the annual equity returns’ profile against the benchmark, Pakistan Stock Exchange (PSX)-KSE 30, has been assessed using machine learning (ML) calibration techniques. The degree of co-movement between an equity and the market index is determined by aligning an approximate multi-factor credit copula model with a standardized regression model. The inconsistent use of explicit regression analysis to demonstrate a stock’s sensitivity to market credit fluctuations is highlighted, along with the contrasting roles of the idiosyncratic stock factor in a one-factor copula model and the regressed error term in the regression model. The simulated financial forecast model anticipates annual equities’ volatility in response to market movements both for auto-correlated stocks and for stocks in the absence of auto-correlation. Additionally, a computationally efficient portfolio optimization scheme is proposed to allocate KSE-30 assets to an optimal portfolio. The roles and placement of highly, less or moderately volatile assets in the optimal portfolio are further discussed.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Algorithmically Efficient Identification of Volatile KSE-30 Equities and Their Role in Optimized Portfolio Allocation

  • 期刊论文

  • 发表日期：

    2025年2月4日

查看全文
  • Nazish Shahid

摘要

To identify the assets contributing to downward market trend, the annual equity returns’ profile against the benchmark, Pakistan Stock Exchange (PSX)-KSE 30, has been assessed using machine learning (ML) calibration techniques. The degree of co-movement between an equity and the market index is determined by aligning an approximate multi-factor credit copula model with a standardized regression model. The inconsistent use of explicit regression analysis to demonstrate a stock’s sensitivity to market credit fluctuations is highlighted, along with the contrasting roles of the idiosyncratic stock factor in a one-factor copula model and the regressed error term in the regression model. The simulated financial forecast model anticipates annual equities’ volatility in response to market movements both for auto-correlated stocks and for stocks in the absence of auto-correlation. Additionally, a computationally efficient portfolio optimization scheme is proposed to allocate KSE-30 assets to an optimal portfolio. The roles and placement of highly, less or moderately volatile assets in the optimal portfolio are further discussed.