Subset Of Stocks Research Articles

Is ‘Herding’ Peculiar to Certain Stocks? A Perspective from the Turkish Stock Market

We test the existence of daily/weekly herding behavior in the Turkish stock market between June 2013 and October 2020 on the stocks that remained listed on the benchmark stock index over the analysis period. Rather than performing the test on a set of stocks belonging to firms with different characteristics as in the literature, we conduct it on subsets of stocks we form based on foreign ownership ratio, firm size (measured by total assets), and prominent financial indicators (price-to-earnings and market-to-book ratios). Our analysis provides no evidence of herding behavior but yields important insights. Specifically, it demonstrates that financial indicators have no bearing on herding behavior, but investor type and firm size may. A slight indication of herding tendency emerges in stocks with a relatively higher investment from local investors but disappears in those with a comparatively higher investment from foreign investors. This finding suggests a potential market knowledge disparity between local and foreign investors, with the less expert being the local group. Moreover, a faint sign of herding tendency also appears in stocks that belong to small firms, possibly due to a heightened uncertainty inherent in such stocks.

Fecundity trends of Chinook salmon in the Pacific Northwest

AbstractFecundity is an important demographic parameter that contributes to the productivity of anadromous fish stock dynamics. Yet, studies on fecundity patterns in Pacific salmon (Oncorhynchusspp.) often only include a few years of data, limiting our ability to understand spatio‐temporal trends. Here, we used data on 43 hatchery Chinook salmon (O. tshawytscha, Salmonidae) populations in Washington State to evaluate whether average fecundity changed over the past three decades. We then used data from a subset of stocks (18) to evaluate the relationship between fecundity and body length. Our results revealed significant changes in fecundity across the 25‐year study period with most stocks showing declines in fecundity over the past decade. Results further showed that Chinook salmon have decreased in length over this same period and that annual variation in mean length explains a majority (62%) of annual variation in mean fecundity. Specifically, we estimated that a 1‐mm reduction in length results in 7.8 fewer eggs (95% CI = 6.6–8.9). Given that the majority of Pacific Northwest Chinook salmon in the environment and harvested in fisheries originate from hatchery releases and that nearby hatchery and wild populations generally have similar ocean distributions, these results likely reflect patterns for many populations not included. Combined, our results highlight the need to consider changes in body size and egg production when assessing the dynamics of anadromous fish populations and designing management or conservation plans, particularly for depressed populations.

ETF Basket-Adjusted Covariance estimation

The increase in trading frequency of Exchanged Traded Funds (ETFs) presents a positive externality for financial risk management when the price of the ETF is available at a higher frequency than the price of the component stocks. The positive spillover consists in improving the accuracy of pre-estimators of the integrated covariance of the stocks included in the ETF basket. The proposed ETF Basket-Adjusted Covariance (BAC) equals the pre-estimator plus a minimal adjustment matrix such that the covariance-implied stock-ETF covariation equals a target value. We focus on a truncated pre-averaged version of the (Hayashi and Yoshida, 2005) pre-estimator and derive the asymptotic properties of its implied stock-ETF covariation. The simulation study confirms that the accuracy gains are substantial in all cases considered. In the empirical part of the paper, we show the gains in tracking error efficiency when using the BAC adjustment to construct portfolios that replicate a broad index using a subset of stocks.

Exploiting Distance-Based Structures in Data Using an Explainable AI for Stock Picking

In principle, the fundamental data of companies may be used to select stocks with a high probability of either increasing or decreasing price. Many of the commonly known rules or used explanations for such a stock-picking process are too vague to be applied in concrete cases, and at the same time, it is challenging to analyze high-dimensional data with a low number of cases in order to derive data-driven and usable explanations. This work proposes an explainable AI (XAI) approach on the quarterly available fundamental data of companies traded on the German stock market. In the XAI, distance-based structures in data (DSD) that guide decision tree induction are identified. The leaves of the appropriately selected decision tree contain subsets of stocks and provide viable explanations that can be rated by a human. The prediction of the future price trends of specific stocks is made possible using the explanations and a rating. In each quarter, stock picking by DSD-XAI is based on understanding the explanations and has a higher success rate than arbitrary stock picking, a hybrid AI system, and a recent unsupervised decision tree called eUD3.5.

Option measures and stock characteristics

An extensive existing literature demonstrates that various option measures (e.g., option-to-stock trading volume ratio) exhibit return predictability in the cross section of stocks. Exploring the fundamental nature and robustness of these findings, we investigate whether this previously identified return predictability of option measures is highly associated with the characteristics or attributes of the underlying stock. We find that the return predictability of option measures is heavily impacted by a subset of stocks whose characteristics also predict future returns, thus providing evidence that stock characteristics are one of the main channels through which option measures capture informed trading.

Beta-Adjusted Covariance Estimation

The increase in trading frequency of Exchanged Traded Funds (ETFs) presents a positive externality for financial risk management when the price of the ETF is available at a higher frequency than the price of the component stocks. The positive spillover consists in improving the accuracy of pre-estimators of the integrated covariance of the stocks included in the ETF. The proposed Beta Adjusted Covariance (BAC) equals the pre-estimator plus a minimal adjustment matrix such that the covariance-implied stock-ETF beta equals a target beta. We focus on the Hayashi and Yoshida (2005) pre-estimator and derive the asymptotic distribution of its implied stock-ETF beta. The simulation study confirms that the accuracy gains are substantial in all cases considered. In the empirical part of the paper, we show the gains in tracking error efficiency when using the BAC adjustment for constructing portfolios that replicate a broad index using a subset of stocks.

Do Proprietary Traders Provide Liquidity?

Proprietary traders’ role in capital markets has received heightened attention with the debate over the Volcker Rule following the 2008-09 financial crisis. To date, there is little evidence on whether proprietary traders provide or take liquidity and how their behavior evolves over the business cycle. Using a unique dataset of proprietary trading activity, we show that proprietary traders concentrate their trades in a subset of stocks that are liquid to begin with. On average, proprietary traders provide liquidity in their trades, but they do so selectively, in large and liquid stocks, and when intermediary balance sheets are strong. Finally, proprietary traders do not increase their liquidity provision during periods of low returns when liquidity dries up.

Mathematical Foundation for Ensemble Machine Learning and Ensemble Portfolio Analysis

In ensemble machine learning we combine decisions of experts to derive at a decision that is better than the individual ones. The process of combining these decisions can be as simple as majority voting or simple averaging or it can be more complicated and involve multiple steps. In this paper we consider the application of ensemble machine learning to the problem of constructing portfolios from individual decisions of multiple experts. We will compare the performance of portfolios constructed by simple averaging and by a novel multistage decision algorithm. This new algorithm constructs a portfolio from subsets of stocks in individual portfolios. Compared to these individual portfolios and a portfolio constructed by simple averaging, the portfolios constructed by proposed method could result in higher annualized return and a modest increase in volatility. We provide extensive numerical comparisons on the viability of the new approach.

Index fund optimization using a hybrid model: genetic algorithm and mixed-integer nonlinear programming

Index funds consist of a subset of stocks, an index tracking portfolio, included in the market index. The index tracking portfolio aims to match the performance of the benchmark index. In this paper, we propose a hybrid model for solving the multiperiod index tracking problem, which includes rebalancing concerns, transaction costs, limits on the number of stocks, and diversification by sector, market capitalization, and stock weight. Our hybrid model combines the genetic algorithm (GA) to select stocks of the index tracking portfolio and mixed-integer nonlinear programming (MINLP) to estimate its weights. Finally, we apply our proposed hybrid model to the S&P500 to find an index tracking portfolio that includes those constraints. The results show that our hybrid model is able to create an index fund whose return rate is similar to the market index with significantly lower risk.

Effects of changes in stock market index composition on stock returns: event study methodology on Zagreb Stock Exchange

Abstract This paper observes the short-run effects of stock market index composition changes on stock returns on the Zagreb Stock Exchange (ZSE). In that way, event study methodology is employed in order to estimate abnormal returns and compare them amongst three subsets of stocks: those leaving the market index, those entering it, and constantly included stocks. The research included 14 regular and extraordinary revisions of the market index in the period from January 2nd, 2015 until March 21st, 2018. The results have confirmed two research hypotheses: stock exclusions from the market index have a negative effect on stock returns on the ZSE, which is consistent with the price pressure hypothesis; and there exist asymmetric effects of index composition changes on stock returns. This is the first study of this kind on the Croatian stock market, thus more questions need to be answered in future research.

A New Value Investing Criterion: The Case of the S&P 500 Index

This paper proposes a new fundamental analysis-based strategy to build a remunerative stock portfolio. The procedure works by selecting an equally weighted small subset of stocks from a broad reference population (for example the constituents of an index) and resetting the selection after some period (for example yearly). The selection is based on six filtering criteria, inspired to the value investing paradigm, aimed at evaluating profitability, financial condition and price convenience of each stock. This active approach is benchmarked against a passive strategy, represented by the Index. As case studies, we consider three separate portfolio selections from popular stock indices: the S&P 500 (from 2000 to 2017), the STOXX Europe 600 (from 2002 to 2017), the S&P 100 (from 2001 to 2018). Such sets of stocks are chosen because of the availability and reliability of financial statements of the companies included therein, a necessary condition to implement the selection methodology we propose. We find that the portfolios selected using the approach described exhibit significantly higher returns than the benchmark.

In Search of the Perfect Hedge Underlying

This report attempts to answer the question: What underlying portfolio should one use to hedge an active fund? We introduce a framework which allows us to conduct analysis on simulated realistic active portfolios in order to build intuition as to how hedge mismatch error affects the level of protection from a given hedge. We show that for typical market conditions, hedge effectiveness improves dramatically when using a hedge portfolio that more accurately reflects the underlying portfolio. This has clear consequences for using generic index options to hedge highly active portfolios. We also showcase several active return and tracking error decompositions that allow one to precisely quantify and thus manage the sources of risk and rewards within a given portfolio. We then discuss a mixed integer quadratic programming formulation that enables us to search across a large investment universe in order to find the subset of stocks that most closely replicates a given portfolio’s performance, whilst simultaneously complying with realistic market constraints. Motivated by these three elements, we introduce several alternative hedging methods for the fund manager to implement a better hedge for their active portfolio. In this report, we focus specifically on the use of long-only and long/short custom basket options as a means of creating an appropriate portfolio hedge.

High-speed detection of emergent market clustering via an unsupervised parallel genetic algorithm

We implement a master-slave parallel genetic algorithm with a bespoke log-likelihood fitness function to identify emergent clusters within price evolutions. We use graphics processing units (GPUs) to implement a parallel genetic algorithm and visualise the results using disjoint minimal spanning trees. We demonstrate that our GPU parallel genetic algorithm, implemented on a commercially available general purpose GPU, is able to recover stock clusters in sub-second speed, based on a subset of stocks in the South African market. This approach represents a pragmatic choice for low-cost, scalable parallel computing and is significantly faster than a prototype serial implementation in an optimised C-based fourth-generation programming language, although the results are not directly comparable because of compiler differences. Combined with fast online intraday correlation matrix estimation from high frequency data for cluster identification, the proposed implementation offers cost-effective, near-real-time risk assessment for financial practitioners.

Supplementary Appendix to 'Modeling the Dependence of Conditional Correlations on Market Volatility'

This Appendix contains details on several technical points and additional empirical results. Sections in this Appendix are indexed by letters and formulas/tables/figures by a letter followed by a number (e.g. A.1). Sections and formulas/tables/figures of the paper are referenced by numbers. In Section A, we expose the estimation procedure of the models employed in the paper. In Section B, we explain the approximation used to avoid the path dependence problem in Markov Switching models. In Section C, we provide the formulas of the marginal impact of volatility on correlations for each VDCC model. In Section D, we detail the estimation method and the results behind our findings about the long-run and short-run effects of the volatility on the correlations. In Section E, we report the application to the three stock data set (and other subsets of stocks) of the method explained in Section 4.1 to evaluate the performance of the constrained RSDC models. In Section F, we include and comment the estimates of the VDCC models for the thirty stock data set used in Section 4.2. Full paper is available at: https://ssrn.com/abstract=2965487

Short-sales constraints and liquidity change: Cross-sectional evidence from the Hong Kong Market

This study investigates the impact of short-sales constraints on liquidity for individual stocks in Hong Kong, as the Hong Kong Stock Market has a special feature such that, at each point of time, only a subset of stocks are allowed to be sold short, with the list of these stocks changing over time. We find that the impact is heterogeneous across stocks: Following the repealing of short-sales constraints, only large, illiquid and inactively traded firms increase in liquidity; while others significantly drop in prices and liquidity. Following the imposing of short-sales constraints, only inactively traded stocks significantly increase in liquidity and prices. The heterogeneous liquidity change also affects the relation between stock overvaluation and one of its necessary conditions — dispersion of investor opinions. When stocks are allowed to be sold short, such a relation is stronger for firms with deteriorating liquidity. When stocks are prohibited from being sold short, this relation disappears among firms with deteriorating liquidity.

Improved alternatives to price multiple and earnings growth ratios used by bottom-up investors

To reduce large files of data into manageable subsets of stocks marked for further review, bottom-up investors utilize spreadsheet software to sort key financial ratios calculated for all equities contained within. Flaws associated with the commonly used price-to-earnings (PE), price-to-book (PB) and expected earnings growth (EG) ratios result in stocks incorrectly included in and excluded from the filtered subsamples. To eliminate these problems, two newly created and two existing ratios are proposed. Of these, the earnings growth yield (EGY) ratio provides the greatest improvement relative to its mainstream competitor. Specifically, EGY is superior to EG in proportionality, numerical interpretation and accuracy of bottom-up stock rankings. Value Line Investment Survey stock screener data is examined to exemplify the magnitude of EG’s interpretation and ranking irregularities, both of which are avoided by the EGY ratio.

A MULTIOBJECTIVE MODEL FOR PASSIVE PORTFOLIO MANAGEMENT: AN APPLICATION ON THE S&P 100 INDEX

Index tracking seeks to minimize the unsystematic risk component by imitating the movements of a reference index. Partial index tracking only considers a subset of the stocks in the index, enabling a substantial cost reduction in comparison with full tracking. Nevertheless, when heterogeneous investment profiles are to be satisfied, traditional index tracking techniques may need different stocks to build the different portfolios. The aim of this paper is to propose a methodology that enables a fund's manager to satisfy different clients’ investment profiles but using in all cases the same subset of stocks, and considering not only one particular criterion but a compromise between several criteria. For this purpose we use a mathematical programming model that considers the tracking error variance, the excess return and the variance of the portfolio plus the curvature of the tracking frontier. The curvature is not defined for a particular portfolio, but for all the portfolios in the tracking frontier. This way funds’ managers can offer their clients a wide range of risk-return combinations just picking the appropriate portfolio in the frontier, all of these portfolios sharing the same shares but with different weights. An example of our proposal is applied on the S&P 100.

Performance replication of the Spot Energy Index with optimal equity portfolio selection: Evidence from the UK, US and Brazilian markets

This paper reproduces the performance of a geometric average Spot Energy Index by investing only in a subset of stocks from the Dow Jones Composite Average, the FTSE 100 and Bovespa Composite indexes, and in two pools that include only energy-sector stocks from the US and the UK respectively. Daily data are used and the index-tracking problem for passive investment is addressed with two evolutionary algorithms – the differential evolution algorithm and the genetic algorithm. The performance of the suggested investment strategy is tested under three different scenarios: buy-and-hold, quarterly and monthly rebalancing, accounting for transaction costs where necessary.

The curvature of the tracking frontier: A new criterion for the partial index tracking problem

Index tracking aims to select portfolios that imitate the behavior of a stock index. A tracking strategy is referred to as partial when the tracking portfolio is solely formed by a subset of stocks, so enabling a substantial cost reduction in comparison with full tracking. Three criteria are usually employed in the literature when building the tracking portfolio: tracking error variance, excess return and tracking portfolio variance. This paper considers a new parameter for use with the above: frontier curvature. This criterion is not defined for a particular portfolio, but for all the portfolios that define the tracking frontier. The main implication is that a manager can satisfy different investment profiles with the same subset of stocks. The manager will therefore reduce transaction costs as all the portfolios on the frontier contain the same stocks.

The Stock Price Response to 13F Disclosures of Positions in IPOs

We examine the stock market's reaction to 13F lings with the SEC. On the day an institution files its 13F, do the prices of stocks held by the institution change? We begin our analysis by examining price responses for initial public off erings of equity, given that the valuations of these stocks are typically more uncertain. We fi nd that the stock market values the news that a top institutional money manager holds a particular IPO. Specifi cally, on the day that an institution in the top 2.5% (based on prior performance) fi les its 13F, any recent IPO reported to be held by that institution enjoys a market-adjusted return of 1%. We plan to investigate other subsets of stocks as well as other subsets of 13F information. Also, we will assess the appropriateness of the market's reaction to the 13F news by examining the stock's performance over future holding periods. This study will shed light on how the market uses information in the 13F disclosures.