nep-fmk New Economics Papers
on Financial Markets
Issue of 2022‒10‒24
six papers chosen by
Kwang Soo Cheong
Johns Hopkins University

  1. Predict stock prices with ARIMA and LSTM By Ruochen Xiao; Yingying Feng; Lei Yan; Yihan Ma
  2. Model-Free Reinforcement Learning for Asset Allocation By Adebayo Oshingbesan; Eniola Ajiboye; Peruth Kamashazi; Timothy Mbaka
  3. A Real Data-Driven Analytical Model to Predict Information Technology Sector Index Price of S&P 500 By Jayanta K. Pokharel; Erasmus Tetteh-Bator; Chris P. Tsokos
  4. Persistence and Volatility Spillovers of Bitcoin price to Gold and Silver prices By Yaya, OlaOluwa A; Lukman, Adewale F.; Vo, Xuan Vinh
  5. Long-Run Linkages between US Stock Prices and Cryptocurrencies: A Fractional Cointegration Analysis By Guglielmo Maria Caporale; José Javier de Dios Mazariegos; Luis A. Gil-Alana
  6. Cyclically Adjusted PE ratio (CAPE) and Stock Market Characteristics in India By Jacob, Joshy; Pradeep, K.P

  1. By: Ruochen Xiao; Yingying Feng; Lei Yan; Yihan Ma
    Abstract: MAE, MSE and RMSE performance indicators are used to analyze the performance of different stocks predicted by LSTM and ARIMA models in this paper. 50 listed company stocks from are selected as the research object in the experiments. The dataset used in this work consists of the highest price on transaction days, corresponding to the period from 01 January 2010 to 31 December 2018. For LSTM model, the data from 01 January 2010 to 31 December 2015 are selected as the training set, the data from 01 January 2016 to 31 December 2017 as the validation set and the data from 01 January 2018 to 31 December 2018 as the test set. In term of ARIMA model, the data from 01 January 2016 to 31 December 2017 are selected as the training set, and the data from 01 January 2018 to 31 December 2018 as the test set. For both models, 60 days of data are used to predict the next day. After analysis, it is suggested that both ARIMA and LSTM models can predict stock prices, and the prediction results are generally consistent with the actual results;and LSTM has better performance in predicting stock prices(especially in expressing stock price changes), while the application of ARIMA is more convenient.
    Date: 2022–08
  2. By: Adebayo Oshingbesan; Eniola Ajiboye; Peruth Kamashazi; Timothy Mbaka
    Abstract: Asset allocation (or portfolio management) is the task of determining how to optimally allocate funds of a finite budget into a range of financial instruments/assets such as stocks. This study investigated the performance of reinforcement learning (RL) when applied to portfolio management using model-free deep RL agents. We trained several RL agents on real-world stock prices to learn how to perform asset allocation. We compared the performance of these RL agents against some baseline agents. We also compared the RL agents among themselves to understand which classes of agents performed better. From our analysis, RL agents can perform the task of portfolio management since they significantly outperformed two of the baseline agents (random allocation and uniform allocation). Four RL agents (A2C, SAC, PPO, and TRPO) outperformed the best baseline, MPT, overall. This shows the abilities of RL agents to uncover more profitable trading strategies. Furthermore, there were no significant performance differences between value-based and policy-based RL agents. Actor-critic agents performed better than other types of agents. Also, on-policy agents performed better than off-policy agents because they are better at policy evaluation and sample efficiency is not a significant problem in portfolio management. This study shows that RL agents can substantially improve asset allocation since they outperform strong baselines. On-policy, actor-critic RL agents showed the most promise based on our analysis.
    Date: 2022–09
  3. By: Jayanta K. Pokharel; Erasmus Tetteh-Bator; Chris P. Tsokos
    Abstract: S&P 500 Index is one of the most sought after stock indices in the world. In particular, Information Technology Sector of S&P 500 is the number one business segment of the S&P 500 in terms of market capital, annual revenue and the number of companies (75) associated with it, and is one of the most attracting areas for many investors due to high percentage annual returns on investment over the years. A non-linear real data-driven analytical model is built to predict the Weekly Closing Price (WCP) of the Information Technology Sector Index of S&P 500 using six financial, four economic indicators and their two way interactions as the attributable entities that drive the stock returns. We rank the statistically significant indicators and their interactions based on the percentage of contribution to the $WCP$ of the Information Technology Sector Index of the S&P 500 that provides significant information for the beneficiary of the proposed predictive model. The model has the predictive accuracy of 99.4%, and the paper presents some intriguing findings and the model's usefulness.
    Date: 2022–09
  4. By: Yaya, OlaOluwa A; Lukman, Adewale F.; Vo, Xuan Vinh
    Abstract: The paper investigated persistence, returns and volatility spill overs from the Bitcoin market to Gold and Silver markets using daily datasets from 2 January 2018 to 31 July 2020. We applied the fractional persistence framework to the price series, returns and volatility proxy series. The results showed that price persistence with Bitcoin posed the highest volatility, while Silver posed the lowest volatility. The results of multivariate GARCH modelling, using the CCC-VARMA-GARCH model and other lower variants indicated the impossibility of returns spill over between Bitcoin and Gold (or Silver) market, while there existed volatility spill overs and these were bi-directional in form of shocks and volatility transmissions. Appropriate portfolio management and hedging strategies rendered towards the end of the paper required more gold and silver investments in the portfolio of Bitcoin to fully have the diversification advantage and reduce risk to the minimum without reducing the portfolio return expectancy.
    Keywords: Bitcoin; Commodity markets; CCC-VARMA-GARCH model; Volatility spill overs; Portfolio management
    JEL: C22
    Date: 2022–09–09
  5. By: Guglielmo Maria Caporale; José Javier de Dios Mazariegos; Luis A. Gil-Alana
    Abstract: This paper applies fractional integration and cointegration methods to examine respectively the univariate properties of the four main cryptocurrencies in terms of market capitalization (BTC, ETH, USDT, BNB) and of four US stock market indices (S&P500, NASDAQ, Dow Jones and MSCI for emerging markets) as well as the possible existence of long-run linkages between them. Daily data from 9 November 2017 to 28 June 2002 are used for the analysis. The results provide evidence of market efficiency in the case of the cryptocurrencies but not of the stock market indices considered. They also indicate that in most cases there are no long-run equilibrium relationships linking the assets in question, which implies that cryptocurrencies can be a useful tool for investors to diversify and hedge when required in the case of the US markets.
    Keywords: stock market prices, cryptocurrencies, persistence, fractional integration and cointegration
    JEL: C22 C58 G11 G15
    Date: 2022
  6. By: Jacob, Joshy; Pradeep, K.P
    Abstract: We estimate the Cyclically Adjusted PE ratio (CAPE) for equity indices in the Indian market. We find the average CAPE ratio of the Indian market is lower than that of the US. Judging the market valuation level based on a long-term moving average of CAPE, we find that the CAPE has remained above the average since 2014. Prominent episodes where CAPE exceeds its average include the period before the 2008 Global Financial Crisis and the post-COVID-19 period. We find that a higher CAPE is associated with lower future returns for holding periods varying from one year to ten years, indicating the negative association between expected returns and CAPE. We also find that a higher CAPE is associated with a greater demand for IPOs by investors and more optimistic earnings forecasts by analysts. Net fundraising through equity significantly increases during periods of high CAPE suggesting rational market timing by firms.
    Date: 2022–09–29

This nep-fmk issue is ©2022 by Kwang Soo Cheong. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.