Multiple Stocks Research Articles

Multi-feature fusion stock prediction based on knowledge graph

PurposeStock prices are subject to the influence of news and social media, and a discernible co-movement pattern exists among multiple stocks. Using a knowledge graph to represent news semantics and establish connections between stocks is deemed essential and viable.Design/methodology/approachThis study presents a knowledge-driven framework for predicting stock prices. The framework integrates relevant stocks with the semantic and emotional characteristics of textual data. The authors construct a stock knowledge graph (SKG) to extract pertinent stock information and use a knowledge graph representation model to capture both the relevant stock features and the semantic features of news articles. Additionally, the authors consider the emotional characteristics of news and investor comments, drawing insights from behavioral finance theory. The authors examined the effectiveness of these features using the combined deep learning model CNN+LSTM+Attention.FindingsExperimental results demonstrate that the knowledge-driven combined feature model exhibits significantly improved predictive accuracy compared to single-feature models.Originality/valueThe study highlights the value of the SKG in uncovering potential correlations among stocks. Moreover, the knowledge-driven multi-feature fusion stock forecasting model enhances the prediction of stock trends for well-known enterprises, providing valuable guidance for investor decision-making.

Multiple stocks recommendation: a spatio-temporal hypergraph learning approach

Multiple stocks recommendation: a spatio-temporal hypergraph learning approach

Change in Foreign Investors’ Strategy From Value Investment to High Frequency Trading

The recent trading stocks and trading patterns of foreigners are different from those evaluated in the literature. Considering this, this study analyzed the changes in foreign investors’ strategy regarding stocks listed on the Korea Exchange from 2005 to 2022. The main results are as follows. First, the top 10 foreigners in transaction value shifted from intensively investing in blue-chip stocks to diversifying investments in multiple stocks. Second, foreigners who trade more than 1,000 stocks a day on average have become a new leading force. Third, as regulations on high frequency trading in the United States and Europe were strengthened, foreigners are moving to Asia for regulation arbitrage. The study also shows that the leading force has shifted from value investment trading to high frequency trading in the domestic stock market.

Stock discrimination of two European squids (Illex coindetii, Loligo forbesii) by statolith shape analysis

AbstractWe evaluated the feasibility of classifying ommastrephid and loliginid squid species by statolith shape analysis into fisheries management units or stocks. Statoliths of Illex coindetii (Verany, 1839) and Loligo forbesii (Steenstrup, 1856) were studied from multiple areas of the North East Atlantic and Northern Mediterranean Sea during 2021–2022. I. coindetii and L. forbesii individuals were categorized into multiple stocks across the areas studied. Stocks migrating between fishing areas as well as multiple stocks in the same area, as identified for L. forbesii in this study, need to be considered for sustainable fisheries management.

Study on Financial Ratio Analysis Used by Investors in Stock Market and Its Impact

Objective: To analyse the demographic and investment patterns of the stock market investors, To understand which financial ratios impacted the investor returns.
 
 Method: The present study used descriptive statistics for understanding the investors. This was followed by applying the discriminant analysis using the tool Advanced Excel. Prepared the structured questionnaire and collected data from the stock market investors. Variables for the study are identified by reviewing the existing the literature. This study followed the descriptive methodology steps for findings and conclusion. Followed steps are literature review, questionnaire preparation, data collection, data cleaning, processing, analyzing them, and conclusion. This study limited to Telangana, India region.
 
 Results and Conclusion:The stock market has investors from all categories of people. Most of them are aged between 20 and 40. We see that having more disposable income is increasing the chances of investing in stock market. As less income people struggle to satisfy their basic needs and have less disposable income. It is observed that most of investors are investing in multiple stocks and not in one bucket. They are interested in diversifying the risks. While investing they are spending time to gather information from all resources. At the time of investment more emphasis is on Growth of company and EPS. Most of the investors not looking at the financial ratios before making decision of investment in stock market. Hence, there is further chance of study to understand why some of the investors not looking at the financial ratios and why taking decision based on different parameters and how they are getting benefited.
 
 Implications of research:Earlier research papers, and studies considered the technical ratio analysis to get the maximum profits, and did the sentiment analysis of the investors, but studies did not consider the opinion of the investors in terms of selection of ratios used for making the investment and get the maximum returns and which financial ratios actually impacted the returns of the investors in the stock market. So, it is the gap of the study.
 
 Originality/value:8%

A study on automated improvement of securities trading strategies using machine learning optimization algorithms

Abstract Automation in securities trading offers advantages over human subjective trading, such as immunity to subjective emotional factors, high efficiency, and the ability to monitor multiple stocks simultaneously, making it a cutting-edge development path in the securities trading industry. In this paper, we first apply the concept of time-frequency decomposition, gradually moving from the first-order moments of securities prices to the higher-order moments. We then combine this with the EMD time-frequency decomposition method to analyze the securities price sequence and extract the characteristics of the securities price fluctuations. Finally, we use the differential long- and short-term memory network to construct an automatic optimization trading system. We compare the system’s performance with traditional technical analysis indexes, as well as the annualized returns of PPO and A2C models on various securities, to verify its performance under unilateral rising, oscillating rising, and plummeting quotes. Finally, we conducted a live test on 1000 GEM stocks. The system in this paper outperforms all traditional technical indicators, with an average annualized return of 71.85% at the lowest and 127.27% at the highest among 5 securities, demonstrating excellent performance. In the three quotes of Ningde Times, Aier Dental, and Goldfish that are rising one way, rising and falling over time, and rising again, the annualized returns of this paper’s system are 77.13%, 67.16%, and 12.66%, which are higher than those of the PPO and A2C models.

Diversification of Jakarta Islamic Index (JII) Stock Optimal Portfolio for the Period 2018-2023

Investment is placing funds into an asset to gain profits in the future through changes in asset prices or capital gains. In Indonesia, stock investment, primarily through the Indonesia Stock Exchange (BEI), is popular among the public. BEI offers various indices, including the Jakarta Islamic Index (JII), which has garnered significant attention. JII comprises stocks of companies that adhere to Sharia principles. In investment, careful analysis is crucial to avoid errors in stock selection. Diversification is a strategy that involves spreading investments across several stocks, aiming to maximize profits while minimizing risks. While the easiest way for investors to enter the stock market is by purchasing the best-performing single stock, relying solely on one stock can be risky if its price drops. This research compares investment outcomes between single-stock and diversified portfolios of two or three stocks, selected based on the Sharpe, Treynor, and Jensen indices. The research analyzes the closing stock prices within the JII index from March 2018 to February 2023. The study results show that diversifying investments across multiple stocks can reduce investment risks, even though it may reduce profit potential.

Stock Prediction Using Machine Learning Methods

The volatility and non-linear nature of the financial stock markets make it incredibly difficult to estimate stock market returns efficiently.. Investors need rapid access to precise information while trading stocks to make intelligent selections. Programable prediction approaches have demonstrated to be increasingly successful in forecasting stock prices with the introduction of artificial intelligence and better computing capacity. However, several variables impact the decision- making process as a stock market trades multiple stocks. Furthermore, it is impossible to forecast the behavior of stock prices. All of these elements make stock price prediction, both vital and tricky. This drives research into the most accurate prediction model that creates the fewest mistakes in its projections. This research studies machine learning approaches and algorithms in an effort to increase the accuracy of stock price prediction. Keywords— Machine Learning, Linear Regression, LSTM, SVM, Decision Tree, Random Forest

Effectiveness Analysis of Stock KDJ Indicator Method based on K-means Clustering

The application of data mining technology expands various techniques in stock investment. Among them, cluster analysis is one of the common means to study stock technical indicators. There is a problem in the current cluster analysis of stock technical indicators -- the lack of validation of large-scale stock technical indicators data sets. Most of them are suitable for the comprehensive analysis of technical indicators of a single stock or multiple stocks. Aiming at this problem, this paper takes "the validity analysis of the large-scale stock KDJ index set method based on K-means clustering" as the theme. Firstly, the k-means clustering algorithm was used to construct a deep analysis model (KDJ-k-means) for the KDJ index set of the Shenzhen Index component data group. Secondly, the K, D and J index sets of 2697 constituent stocks of Shenzhen Composite Index are analyzed experimentally. Finally, the results of integrated data mining are obtained. The KDJ-k-means model is an optimization scheme based on the KDJ index set using clustering technology, which provides an intuitive and efficient visual application for deep analysis of large-scale stock data groups.

A novel time series prediction method based on pooling compressed sensing echo state network and its application in stock market

In the prediction of time series, the echo state network (ESN) exhibits exclusive strengths and a unique training structure. Based on ESN model, a pooling activation algorithm consisting noise value and adjusted pooling algorithm is proposed to enrich the update strategy of the reservoir layer in ESN. The algorithm optimizes the distribution of reservoir layer nodes. And the nodes set will be more matched to the characteristics of the data. In addition, we introduce a more efficient and accurate compressed sensing technique based on the existing research. The novel compressed sensing technique reduces the amount of spatial computation of methods. The ESN model based on the above two techniques overcomes the limitations in traditional prediction. In the experimental part, the model is validated with different chaotic time series as well as multiple stocks, and the method shows its efficiency and accuracy in prediction.

LOB modeling using Hawkes processes with a state-dependent factor

A point process model for order flows in limit order books is proposed, in which the conditional intensity is the product of a Hawkes component and a state-dependent factor. In the LOB context, state observations may include the observed imbalance or the observed spread. Full technical details for the computationally-efficient estimation of such a process are provided, using either direct likelihood maximization or EM-type estimation. Applications include models for bid and ask market orders, or for upwards and downwards price movements. Empirical results on multiple stocks traded in Euronext Paris underline the benefits of state-dependent formulations for LOB modeling, e.g. in terms of goodness-of-fit to financial data.

Naïve Buying Diversification and Narrow Framing by Individual Investors

ABSTRACTWe provide the first tests to distinguish whether individual investors equally balance their overall portfolios (naïve portfolio diversification, NPD) or, in contrast, equally balance the values of same‐day purchases of multiple assets (naïve buying diversification, NBD). We find NBD in purchases of multiple stocks, and in mixed purchases of individual stocks and funds. In contrast, there is little evidence of NPD. Evidence suggests that NBD arises due to stock picking behavior and neglect of diversification. These findings suggest that behavioral finance theory should incorporate transaction, as well as portfolio, framing.

A Deep Learning Model for Predicting Stock Prices in Tanzania

Stock price prediction models help traders to reduce investment risk and choose the most profitable stocks. Machine learning and deep learning techniques have been applied to develop various models. As there is a lack of literature on efforts to utilize such techniques to predict stock prices in Tanzania, this study attempted to fill this gap. This study selected active stocks from the Dar es Salaam Stock Exchange and developed LSTM and GRU deep learning models to predict the next-day closing prices. The results showed that LSTM had the highest prediction accuracy with an RMSE of 4.7524 and an MAE of 2.4377. This study also aimed to examine whether it is significant to account for the outstanding shares of each stock when developing a joint model for predicting the closing prices of multiple stocks. Experimental results with both models revealed that prediction accuracy improved significantly when the number of outstanding shares of each stock was taken into account. The LSTM model achieved an RMSE of 10.4734 when the outstanding shares were not taken into account and 4.7524 when they were taken into account, showing an improvement of 54.62%. However, GRU achieved an RMSE of 12.4583 when outstanding shares were not taken into account and 8.7162 when they were taken into account, showing an improvement of 30.04%. The best model was implemented in a web-based prototype to make it accessible to stockbrokers and investment advisors.

Application of Mean-Variance Model for Firefighter

A good investment portfolio can make the investment get more returns, which requires investors to adopt appropriate methods to optimize the investment portfolio. A portfolio is not just a simple sum of assets, it requires the use of suitable models to analyze optimal asset allocation. This paper analyzes the asset allocation of firefighters, and uses three methods of mean variance analysis, CAPM model and FF3F model to optimize the pension investment ratio of firefighters. At the same time, this paper analyzes multiple stocks from four industries including retail, technology, manufacturing, and food, and strives to find the investment portfolio with the most potential pension. The results show that in CAPM, the largest weights of both maximum sharp ratio portfolio and the minimum portfolio belong to the possession of ‘NSRGY’, while in the FF3F model, the greatest weight of the maximum sharp ratio portfolio belongs to ‘TM’ possession and the greatest weight of the minimum variance portfolio belongs to ‘NSRGY’. This research could help retirees on the same pension type better allocate their pension assets and optimize their investment portfolios. At the same time, this paper also analyzes the investment performance of stocks in different industries under the same fixed proportion of pension.

Weak range-wide population structure in the blackfin tuna (Thunnus atlanticus) revealed by analysis of genome-wide SNPs

Abstract Blackfin tuna (Thunnus atlanticus) is a small tuna distributed in the western Atlantic Ocean where it is exploited by growing recreational and commercial regional fisheries. In this work, genome-wide genetic variation was analysed to investigate the occurrence of stock subdivision. A de novo assembly of the blackfin tuna genome was generated using Illumina paired-end sequencing data and applied as a reference for population genomic analysis of specimens from nine localities (average sample size per locality n = 72) spanning most of the blackfin tuna distribution range. A total of 2139 single-nucleotide polymorphisms were discovered and genotyped using the double-digest restriction associated DNA sequencing. Pairwise exact homogeneity tests were significant in 24 out of 36 population pairs and significant spatial autocorrelation of genotypes was observed for specimens collected within 2250 km of each other. However, divergence among locality samples was very low (pairwise FST range 0.0002–0.0025) and significant temporal variations were detected in localities sampled multiple times. Approaches to detect cryptic groups de novo were unsuccessful. Additional sampling is warranted to determine if multiple stocks need to be defined for management and assess temporal and spatial patterns of gene flow connecting them.

Mitochondrial genetic variation in bowhead whales in the western Arctic

Bowhead whales in the Western Arctic are managed as a single stock by the International Whaling Commission (IWC). In response to recent concerns about the potential existence of multiple stocks in the region, we examined genetic variation in the mitochondrial control region among various spatial, temporal and age-related strata. Sequences from 382 samples were used in the comparisons. No significant differences were detected in spatial comparisons or in temporal comparisons along Alaska’s North Slope. However the cc2 analysis showed evidence of genetic heterogeneity between some of the age cohorts, specifically between animals born prior to 1918 (n=8) and those born after 1979 (n=34) (p=0.030), between those born 1918-1949 (n=13) and those born after 1979 (p=0.050), and between the two aforementioned older cohorts and those born after 1979 (p=0.009). There was also a significant Fst difference between autumn (n=13) and spring (n=11) whales from St. Lawrence Island (p=0.049). The age data were insufficient to determine if this seasonal difference was due in part to the difference between age cohorts.

Assessment of Antarctic minke whales using statistical catch-at-age analysis (SCAA)

Statistical catch-at-age analysis (SCAA) is applied to data for Antarctic minke whales. The SCAA model is spatially-structured, can model multiple stocks of minke whales, and can utilise several data types for parameter estimation. The application to Antarctic minke whales considers two stocks (I and P) in five areas which cover Antarctic Areas III–E to VI–W. The parameters of the model (annual deviations about the stock-recruitment relationship, changes over time in carrying capacity, density-dependence parameters related to productivity and carrying capacity, and the parameters which determine growth by stock, age-specific natural mortality by stock, and vulnerability by area and ‘fleet’) are estimated by fitting the model to data on catches, catch-at-length, conditional age-at-length, and estimates of absolute and relative abundance. A reference case analysis is selected, and sensitivity explored using retrospective analyses and by varying the assumptions on which the reference case analysis is based. The reference case analysis is able to mimic all of the data sources adequately. Most of the analyses (reference and sensitivity) indicates that Antarctic minke whales in the assessed area increased from 1930 until the mid-1970s and have declined thereafter, with the extent of the decline greater for minke whales in Antarctic Areas III–E to V–W than for those further east. Natural mortality is consistently estimated to be higher for younger and older individuals than for individuals of intermediate age. Estimates of MSYR1+ (the exploitation rate on animals 1 and older at which sustainable yield is maximised) are presented, but are unreliable owing to the lack of contrast.

Evidence of multiple stocks of catfish, Rita rita (Hamilton), from the Ganges Basin on the basis of an integrated analysis of truss morphometrics, otolith microchemistry, and otolith shape

Context Management of Rita rita (Hamilton) in India is hampered by a lack of understanding of possible stock structure. Aim To investigate possible spatial stock structure of Rita rita in the Ganges Basin. Methods Independent analyses of landmark-based truss morphometry, otolith elemental analysis and otolith shape were conducted to investigate the stock structure of the catfish (Rita rita) from the Ganga River and its tributaries Yamuna and Ramganga. Key results Each of the stock-delineation approaches, namely, truss morphometrics, otolith elemental composition and otolith shape, showed significant differences among the fish groups from three sampling locations (P ≤ 0.003). Despite these differences, reclassification analyses showed variable (although all greater than random) reclassification rates (truss morphometry: 78%, otoliths elemental data: 98%, otolith shape: 50%). Conclusions An integrated view of the three analyses suggested spatial structuring and that there may be multiple stocks of Rita rita in the Ganges Basin. Implications Future investigations should consider possible variations in demographic parameters that may affect fisheries management. The multiple-lines-of-evidence approach taken in this study can serve as a template for studies of other species in any region.

Pricing rainbow option for uncertain financial market

Rainbow option refers to the option whose payoff depends on at least two underlying risky assets, which is justifiably one of the most significant tool to hedge risk brought by the uncertainty from financial market. Hence, option pricing problem is always an issue with great attention. In this paper, we assume that the multiple dynamic stock prices obey uncertain differential equations without sharing dividends in the framework of uncertainty theory. Then we discuss the rainbow option pricing problem for multiple stocks in a financial market with uncertain information, give the concepts and derive pricing formulas for five scenarios including maximum call, minimum call, maximum put, minimum put, and put on 2 and call on 1. Moreover, some corresponding examples are respectively taken to illustrate the pricing formulas in five cases.

Distribution, abundance and sighting patterns of multiple stocks of bottlenose dolphins (Tursiops truncatus) in coastal Virginia waters

Three stocks of bottlenose dolphins (Tursiops truncatus) are currently known to co‐occur in the coastal waters off Virginia. A combination of visual line‐transect survey and photo‐identification (photo‐ID) methods was used to gather information on the occurrence, distribution and density of bottlenose dolphins in the coastal areas of Norfolk and Virginia Beach. Sixty‐one line‐transect surveys were completed in two zones (inshore and offshore) between August 2012 and August 2015, with on‐effort coverage of 6,550 kilometres (km) of trackline over 349.6 hours. Conventional line‐transect analysis of bottlenose dolphin sightings showed both spatial and temporal variation in density (D) and abundance (N), with highest density in the inshore zone during warm‐water months (June–November). Inshore densities were calculated as 3.51 individuals per square kilometre (km2) (N = 1,090) in the warm‐water season and 0.73 individuals/km2 (N = 225) in cool‐water months (December–May). Densities in the offshore zone were 1.24 individuals/km2 (N = 741) in the warm‐water season and 0.61 individuals/km2 (N = 366) in the cool‐water season. Warm‐water density peaks support previous research; however, this study documents a cold‐season presence of dolphins in both zones not previously reported. Twenty‐seven photo‐ID surveys were completed and a photo‐ID catalogue was created using photos taken during both dedicated photo‐ID and line‐transect surveys, containing 1,335 unique individuals. Re‐sighting numbers were low, with less than 17% of individuals documented on more than one occasion, and only 4% sighted on three or more occasions, with a maximum of 4 re‐sightings. Days between re‐sightings ranged from 5 to 970, though distance between re‐sightings spanning greater time was minimal (less than 25km). Sighting locations of photo‐IDed dolphins were broken into three regions to investigate seasonal and spatial patterns of individual distribution; dolphins sighted only in the Cape Henry (CH) or Inner Bay (IB) region were observed mostly during summer and fall seasons (93% CH, 100% IB) with none occurring during winter. For the Outer Coastline (OC) region, the majority of sightings (88%) occurred during fall and winter. Additionally, there were two individuals sighted during winter months also sighted during summer more than 130km to the north inside Chesapeake Bay (matched to a different catalogue). These sightings support the possibility that the current stock structure does not account for all dolphins in the region. Stock structure as currently understood is complicated, with overlapping spatial distribution of three stocks that separate seasonally. Our study provides information that may be useful for management, but also additional findings that could impact future stock designations