Search results

This paper aims to propose an improved version of portfolio optimization model through the prediction of the future behavior of stock returns using a combined wavelet-based long short-term memory (LSTM).

First, data are gathered and divided into two parts, namely, “past data” and “real data.” In the second stage, the wavelet transform is proposed to decompose the stock closing price time series into a set of coefficients. The derived coefficients are taken as an input to the LSTM model to predict the stock closing price time series and the “future data” is created. In the third stage, the mean-variance portfolio optimization problem (MVPOP) has iteratively been run using the “past,” “future” and “real” data sets. The epsilon-constraint method is adapted to generate the Pareto front for all three runes of MVPOP.

The real daily stock closing price time series of six stocks from the FTSE 100 between January 1, 2000, and December 30, 2020, is used to check the applicability and efficacy of the proposed approach. The comparisons of “future,” “past” and “real” Pareto fronts showed that the “future” Pareto front is closer to the “real” Pareto front. This demonstrates the efficacy and applicability of proposed approach.

Most of the classic Markowitz-based portfolio optimization models used past information to estimate the associated parameters of the stocks. This study revealed that the prediction of the future behavior of stock returns using a combined wavelet-based LSTM improved the performance of the portfolio.

In capital markets research, analysts’ consensus forecasts are widely used as a proxy for unobservable market earnings expectation. However, they measure the market earnings expectation with error that may vary cross-sectionally, as the market does not consistently rely on analysts’ consensus forecasts to form earnings expectation (Walther, 1997). Based on this notion, this paper aims to relate the prediction of future stock returns to the cross-sectional variation of the error in measuring market earnings expectation embedded in analysts’ consensus forecasts.

This study uses empirical analyses based on stock returns and annual analysts’ consensus forecasts.

Based on the analytical work by Abarbanell et al. (1995), this study reports that when the measurement error in annual analysts’ consensus forecasts is the smallest, forward earnings-to-price ratio (constructed with annual analysts’ consensus forecasts) best explains future stock returns, and the forward earnings-to-price ratio-based investment strategy is the most profitable.

Findings of this study are useful to capital markets research that relies on the market earnings expectation and to practitioners seeking more profitable investment strategies.

This study aims to use gray models to predict abnormal stock returns.

Data are collected from listed companies in the Tehran Stock Exchange during 2005-2015. The analyses portray three models, namely, the gray model, the nonlinear gray Bernoulli model and the Nash nonlinear gray Bernoulli model.

Results show that the Nash nonlinear gray Bernoulli model can predict abnormal stock returns that are defined by conditions other than gray models which predict increases, and then after checking regression models, the Bernoulli regression model is defined, which gives higher accuracy and fewer errors than the other two models.

The stock market is one of the most important markets, which is influenced by several factors. Thus, accurate and reliable techniques are necessary to help investors and consumers find detailed and exact ways to predict the stock market.

Stock market forecasters are focusing to create a positive approach for predicting the stock price. The fundamental principle of an effective stock market prediction is not only to produce the maximum outcomes but also to reduce the unreliable stock price estimate. In the stock market, sentiment analysis enables people for making educated decisions regarding the investment in a business. Moreover, the stock analysis identifies the business of an organization or a company. In fact, the prediction of stock prices is more complex due to high volatile nature that varies a large range of investor sentiment, economic and political factors, changes in leadership and other factors. This prediction often becomes ineffective, while considering only the historical data or textural information. Attempts are made to make the prediction more precise with the news sentiment along with the stock price information.

This paper introduces a prediction framework via sentiment analysis. Thereby, the stock data and news sentiment data are also considered. From the stock data, technical indicator-based features like moving average convergence divergence (MACD), relative strength index (RSI) and moving average (MA) are extracted. At the same time, the news data are processed to determine the sentiments by certain processes like (1) pre-processing, where keyword extraction and sentiment categorization process takes place; (2) keyword extraction, where WordNet and sentiment categorization process is done; (3) feature extraction, where Proposed holoentropy based features is extracted. (4) Classification, deep neural network is used that returns the sentiment output. To make the system more accurate on predicting the sentiment, the training of NN is carried out by self-improved whale optimization algorithm (SIWOA). Finally, optimized deep belief network (DBN) is used to predict the stock that considers the features of stock data and sentiment results from news data. Here, the weights of DBN are tuned by the new SIWOA.

The performance of the adopted scheme is computed over the existing models in terms of certain measures. The stock dataset includes two companies such as Reliance Communications and Relaxo Footwear. In addition, each company consists of three datasets (a) in daily option, set start day 1-1-2019 and end day 1-12-2020, (b) in monthly option, set start Jan 2000 and end Dec 2020 and (c) in yearly option, set year 2000. Moreover, the adopted NN + DBN + SIWOA model was computed over the traditional classifiers like LSTM, NN + RF, NN + MLP and NN + SVM; also, it was compared over the existing optimization algorithms like NN + DBN + MFO, NN + DBN + CSA, NN + DBN + WOA and NN + DBN + PSO, correspondingly. Further, the performance was calculated based on the learning percentage that ranges from 60, 70, 80 and 90 in terms of certain measures like MAE, MSE and RMSE for six datasets. On observing the graph, the MAE of the adopted NN + DBN + SIWOA model was 91.67, 80, 91.11 and 93.33% superior to the existing classifiers like LSTM, NN + RF, NN + MLP and NN + SVM, respectively for dataset 1. The proposed NN + DBN + SIWOA method holds minimum MAE value of (∼0.21) at learning percentage 80 for dataset 1; whereas, the traditional models holds the value for NN + DBN + CSA (∼1.20), NN + DBN + MFO (∼1.21), NN + DBN + PSO (∼0.23) and NN + DBN + WOA (∼0.25), respectively. From the table, it was clear that the RMSRE of the proposed NN + DBN + SIWOA model was 3.14, 1.08, 1.38 and 15.28% better than the existing classifiers like LSTM, NN + RF, NN + MLP and NN + SVM, respectively, for dataset 6. In addition, he MSE of the adopted NN + DBN + SIWOA method attain lower values (∼54944.41) for dataset 2 than other existing schemes like NN + DBN + CSA(∼9.43), NN + DBN + MFO (∼56728.68), NN + DBN + PSO (∼2.95) and NN + DBN + WOA (∼56767.88), respectively.

This paper has introduced a prediction framework via sentiment analysis. Thereby, along with the stock data and news sentiment data were also considered. From the stock data, technical indicator based features like MACD, RSI and MA are extracted. Therefore, the proposed work was said to be much appropriate for stock market prediction.

This paper sets out to apply chaos theory to the prediction of stock returns using Greek and Turkish stock index data. The aim of the analysis is to empirically show whether the markets have informational efficiency, in a comparative perspective.

The research employs Grassberger and Procaccia's methodology in the time series analysis in order to estimate the correlation and minimum embedding dimensions of the corresponding strange attractor. To achieve out of the sample multistep ahead prediction, the paper gives the average for overall neighbours' projections of k‐steps into the future.

The results display the fact that the chaos theory is suitable to examine the time series of stock index returns. The empirical findings show that the stock markets are efficient in Greece, though in Turkey the market is predictable. The main practical implication of the findings is that the technical analysis works in Turkish markets and it is possible to beat the market, while in Greece the fundamental analysis works for equity trading.

The research results have both methodological and practical originality. On the theoretical side, the research shows how the chaos theory can be applied in financial time series analysis. The model is employed with data from Greece, as an EU member; and Turkey, as a candidate to the EU. The fact that the model works in Turkey implies that chaos theory can be used in emerging economies as a prediction model. On the practical side, the paper contributed to the previous literature by providing empirical evidence on market efficiency using a stochastic model.

This study examines the ability of fundamental summary measure Pr to predict earnings change for the subsequent year, the association of Pr and stock returns, and the relationship between Pr and risk factors beta and size. Pr is a probability index generated by logistic model and financial statement data. Beta effect is minimized by grouping firms into beta portfolios while size is controlled through incorporating size as an independent variable in the regression models. Evidence from the study indicates that Pr has a strong ability to predict future earnings change and has a positive and significant association with adjusted market returns, after controlling for beta. Pr's association with adjusted market returns is mitigated when beta and size are controlled simultaneously.

Equity research in experimental psychology reveals investors' overreactions to bad news events. This study of asymmetric price structures in equity markets investigates whether such behavior predicts stock returns in an emerging market of India.

The research decomposes Bombay Stock Exchange (BSE) Sensex returns into Extremely Positive Returns (EPR) and Extremely Negative Returns (ENR) based on extreme values at first and then tests their lead–lag relations.

The empirical finding is consistent with the existing evidence of asymmetric news effects on stock returns in India. In precise, ENR robustly predicts one-month-ahead EPR for the sample period from January 1991 to March 2020. This predictive power persists even in the presence of popular valuation ratios and business cycle variables.

The paper explains the rationale of extreme value modeling in price forecasting. Investors can find additional utility gains from market cycle information while predicting extreme returns in Indian stock market.

The paper is unique to understand business cycle effects in extreme return reversals in emerging markets.

This paper aims to use artificial neural network (ANN) methods to predict stock price crashes in the Chinese equity market.

Three ANN models are developed and compared with the logistic regression model.

Results from this study conclude that the ANN approaches outperform the traditional logistic regression model, with fewer hidden layers in the ANN model having superior performance compared to the ANNs with multiple hidden layers. Results from the ANN approach also reveal that foreign institutional ownership, financial leverage, weekly average return and market-to-book ratio are the important variables when predicting stock price crashes, consistent with results from the traditional logistic model.

First, the ANN framework has been used in this study to forecast the stock price crashes and compared to the traditional logistic model in the world’s largest emerging market China. Second, the receiver operating characteristics curves and the area under the ROC curve have been used to evaluate the forecasting performance between the ANNs and the traditional approaches, in addition to some traditional performance evaluation methods.

A one-year-ahead price change forecasting model is proposed based on the fundamental analysis to examine the relationship between equity market value and financial performance measures. By including book value and six financial statement items in the valuation model, current firm value can be determined and the estimation error can predict the direction and magnitude of future returns of a given portfolio. The six financial performance measures represent both cash flows – cash flows from operations (CFO), cash flows from investing (CFI), and cash flows from financing (CFF) – as well as net income – R&D expenditures (R&D), operating income (OI), and adjusted nonoperating income (ANOI). This study uses a 10-year sample of the Taiwan information electronic industry (1995–2004 with 2,465 firm-year observations). We find hedge portfolios (consisting of a long position in the most underpriced portfolio and an offsetting short position in the most overpriced portfolio) provide an average annual return of 43%, more than three times the average annual stock return of 12.6%. The result shows the estimation error can be a good stock return predictor; however, the return of hedge portfolios generally decreases as the market matures.

Even though most previous research studies suggest that the relationship between common financial ratios and stock returns is linear, recent studies by Mramor and Mramor‐Kosta (1997), and Mramor and Pahor (1998) show that such a linear relationship might not generally exist. In this study, we model the relationships between common financial ratios and stock returns from 1996 to 2000 using linear and non‐linear forms for a sample of 46 Egyptian firms. Our empirical findings suggest that non‐linear relationships exist and are more descriptive of the behavior of stock returns.