Forecasting Stock Price Trends by Analyzing Economic Reports With Analyst Profiles

Suzuki, Masahiro; Sakaji, Hiroki; Izumi, Kiyoshi; Ishikawa, Yoshinori

doi:10.3389/frai.2022.866723

Cited by 3 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The relationship between analyst forecasts and stock prices is supported by research (Yahaya, 2021), which shows that institutional trading and analyst forecasts have an impact on the stock market. The results of the research belonging to (Niederhoffer & Regan, 2018) show that the stock price is highly dependent on changes in earnings, both absolute and relative to analyst forecasts (Suzuki et al, 2022). The results show that there is a strong and significant relationship between the forecast error and the subsequent movement of the stock price (Renfro, 2015).…”

Section: Effect Of Analyst Forecast and Stock Pricementioning

confidence: 99%

“…Analysts' forecasts are an important source of information for investors (Sancetta Giuseppe; Renzi Antonio; Orlando, 2012). Investors need to look for market information such as stock prices and fundamental information such as company sales, earnings, and business conditions (Suzuki, Sakaji, Izumi, & Ishikawa, 2022). If analysts are biased in what they forecast, the information can be misused by certain parties.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Meta-Analysis of Forecast Analysis on Stock Price

Hananto,

Purnamasari

2023

Indones. J. Econ. Manag.

View full text Add to dashboard Cite

Analysts' views on economic risk can be an important part of an investor's investment decision-making process. Several researchers have conducted research on analyst forecasts and stock prices. However, we need to look at the consistency of the results of previous studies in order to draw general conclusions. This must be done to prove whether analyst forecasts affect stock prices. The consistency of results in this study was determined using a meta-analysis method. This method is supported by the CMA (Comprehensive Meta-Analysis) software. Meta-analysis provides an estimate of the effect size to measure the relationship between the independent variable (analyst forecast) and the dependent (stock price). The heterogeneity test results show that I-squared is > 50 percent, which means high heterogeneity. The correlation analysis results show a p-value of 0.004, meaning that analyst forecast studies on stock prices are heterogeneous. Heterogeneity refers to differences in data within each study or between major studies. The results in this study are heterogeneous, caused by high sampling error when the research location for each sample is different due to differences in economic conditions. Therefore, analyst forecasts have an effect on stock prices.

show abstract

Section: Effect Of Analyst Forecast and Stock Pricementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Meta-Analysis of Forecast Analysis on Stock Price

Hananto,

Purnamasari

2023

Indones. J. Econ. Manag.

View full text Add to dashboard Cite

show abstract

“…In addition, research has been conducted on the creation of an economic index using rate information from analyst reports [6,10]. Several studies use text mining of analyst reports to predict stock prices [20,21]. The novelty of the current study is that the masked language model (MLM) score was used to create the polarity index to index the tone of the financial text.…”

Section: Creation Of Economic Index Using Text Miningmentioning

confidence: 99%

Constructing Sentiment Signal-Based Asset Allocation Method with Causality Information

Taguchi,

Sakaji,

Izumi

et al. 2023

New Gener. Comput.

Self Cite

View full text Add to dashboard Cite

This study demonstrates whether financial text is useful for the tactical asset allocation method using stocks. This can be achieved using natural language processing to create polarity indexes in financial news. We perform clustering of the created polarity indexes using the change point detection algorithm. In addition, we construct a stock portfolio and rebalanced it at each change point using an optimization algorithm. Consequently, the proposed asset allocation method outperforms the comparative approach. This result suggests that the polarity index is useful for constructing the equity asset allocation method.

show abstract

FinDeBERTaV2: Word-Segmentation-Free Pre-trained Language Model for Finance

Suzuki,

Sakaji,

Hirano

et al. 2024

Transactions of the Japanese Society for Artificial Intelligenc

View full text Add to dashboard Cite

Financial documents are increasing year by year, and natural language processing (NLP) techniques are widely applied to process these documents. Specifically, Transformer-based pre-trained models such as BERT have been successful in NLP in recent years. These cutting-edge models have been adapted to the financial domain by pretraining with financial corpora, while most financial pre-trained models are BERT-based and do not benefit from the mechanisms of recent state-of-the-art models. Many Japanese models need to perform word segmentation based on morphological analysis, which may reduce portability and processing efficiency. In this study, we show that models without pre-word segmentation have no performance disadvantage over models with pre-word segmentation in both the financial and general domains, while the models without pre-word segmentation may benefit from reduced computational complexity and increased model processing efficiency due to a reduced number of tokens. The length of tokens had little effect on the performance of the downstream classification tasks. We build both general models and financial models without pre-word segmentation on a large scale. We show that our financial pre-trained models perform better than conventional models on classification tasks in the financial domain, and that the general models can be good baselines to adapt to specialized domains. Our evaluation experiments show that additional pre-training is effective because it takes advantage of the performance of models constructed from large general corpora. We have released the pre-trained models at https://huggingface.co/izumi-lab. * 1 現所属：株式会社 Preferred Networks (Preferred Networks, Inc.) * 2 現所属：北海道大学大学院情報科学研究院 (

show abstract

Forecasting Stock Price Trends by Analyzing Economic Reports With Analyst Profiles

Cited by 3 publications

References 30 publications

Meta-Analysis of Forecast Analysis on Stock Price

Meta-Analysis of Forecast Analysis on Stock Price

Constructing Sentiment Signal-Based Asset Allocation Method with Causality Information

FinDeBERTaV2: Word-Segmentation-Free Pre-trained Language Model for Finance

Contact Info

Product

Resources

About