A Novel Ensemble Learning Approach for Stock Market Prediction Based on Sentiment Analysis and the Sliding Window Method

Chiong, Raymond; Fan, Zongwen; Hu, Zhongyi; Dhakal, Sandeep

doi:10.1109/tcss.2022.3182375

Cited by 15 publications

(10 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The AI domain is categorized by new technologies, including facial recognition, virtual assistants, chatbots, robots, blockchains, mapping, machine learning and deep learning (Chiong et al, 2022;Chiong et al, 2023;Chopra, 2019;Sun et al, 2020). These technologies Inducing AI-powered chatbot use fundamentally upgrade firms' business practices, affect organizational decision-making and redefine management models (Kshetri, 2021), leading to enhanced core competency and business processes, such as service quality, customer satisfaction and purchase decisionmaking.…”

Section: Rq2 What Factors Induce Purchase Intention When Chatbots Are...mentioning

confidence: 99%

Inducing AI-powered chatbot use for customer purchase: the role of information value and innovative technology

2023

JSIT

View full text Add to dashboard Cite

Purpose This study aims to understand a customer-purchase mechanism in the artificial intelligence (AI)-powered chatbot context based on the elaboration likelihood model (ELM) and technology acceptance model (TAM). The first objective is to examine how to boost chatbot adoption. The second objective is to investigate the role of information characteristics, technology-related characteristics and attitude toward AI in purchase intention. Design/methodology/approach Data was collected from a sample of 492 users in Vietnam, who are potential customers of chatbots for purchase. Structural equation modeling was applied for data analysis. Findings Results illustrate that chatbot adoption is significantly influenced by information credibility, technology-related factors (i.e. interactivity, relative advantage and perceived intelligence), attitude toward AI and perceived usefulness. Moreover, information quality and persuasiveness motivate information credibility. Information credibility and attitude toward AI are the essential motivations for perceived usefulness. Finally, chatbot adoption and information credibility determine purchase intention. Practical implications The results are insightful for practitioners to envisage the importance of chatbot use for customer purchase in the AI scenario. Additionally, this research offers a framework to practitioners for shaping customer engagement in chatbots. Originality/value The value of this work lies in the incorporation of technology-related characteristics into the two well-established theories, the ELM and TAM, to identify the importance of AI and its applications (i.e. chatbots) for purchase and to understand the formation of perceived usefulness and chatbot use through information credibility and attitude toward AI.

show abstract

Section: Rq2 What Factors Induce Purchase Intention When Chatbots Are...mentioning

confidence: 99%

Inducing AI-powered chatbot use for customer purchase: the role of information value and innovative technology

2023

JSIT

View full text Add to dashboard Cite

show abstract

“…Our experiment's longest training period is 19 years (1998)(1999)(2000)(2001)(2002)(2003)(2004)(2005)(2006)(2007)(2008)(2009)(2010)(2011)(2012)(2013)(2014)(2015)(2016); hence, the training datasets are likely to have outdated problems. Therefore, this paper employed the sliding window technique, controlling the length of training periods identically (Chiong et al, 2022;Javid et al, 2020), to solve the inconsistent problem and address the concern about overfitting and obsolete data. In subsection 5.2, a 10-year sliding window-based supplement test is implemented.…”

Section: Comparison Of the Models' Performancementioning

confidence: 99%

Predicting accounting fraud using imbalanced ensemble learning classifiers – evidence from China

Rahman

Zhu

2023

Accounting & Finance

View full text Add to dashboard Cite

The current research aims to launch effective accounting fraud detection models using imbalanced ensemble learning algorithms for China A‐Share listed firms. Based on a sample of 33,544 Chinese firm‐year instances from 1998 to 2017, this research respectively established one logistic regression and four ensemble learning classifiers (AdaBoost, XGBoost, CUSBoost, and RUSBoost) by 12 financial ratios and 28 raw financial data. Additionally, we divided the sample into the train and test observations to evaluate the classifiers' out‐of‐sample performance. In detail, we applied two metrics, namely, Area under the ROC (receiver operating characteristic) curve (AUC) and Area under the Precision‐Recall curve (AUPR), to evaluate classifiers' discriminability. In the supplement test, this study put forward an algebraic fused model on the basis of the four ensemble learning classifiers and introduced the sliding window technique. The empirical results showed that the ensemble learning classifiers can detect accounting fraud for the imbalanced China A‐listed firms far more effectively than the logistic regression model. Moreover, imbalanced ensemble learning classifiers (CUSBoost and RUSBoost) effectively performed better than the common ensemble learning models (AdaBoost and XGBoost) in average. The algebraic fused model in the supplement test also obtained the highest average AUC and AUPR among all the employed algorithms. Our results offer firm support for the potential role of Machine Learning (ML)‐based Artificial Intelligence (AI) approaches in reliably predicting accounting fraud with high accuracy. Similarly, for the Chinese settings, our ML‐based AI offers utmost advantage in forecasting accounting fraud. Finally, this paper fills the research gap on the applications of imbalanced ensemble learning in accounting fraud detection for Chinese listed firms.

show abstract

“…The paper [10] proposes an ensemble learning approach for predicting the stock market based on sentiment analysis and the sliding window method. Using several natural language processing approaches, the authors extract sentiment elements from social media and financial news data.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Metrics DiSRAN [11] 53.8% pr Ensemble RNN [10] 59.71% acc SVM [8] 79.08% acc IMN [14] 83.89% acc EPR+R-ANN [6] 86.57 pr AECLSTM [9] 96.3% acc Proposed Method (GPT embeddings) 98.6%acc, 99%pr…”

Section: Modelmentioning

confidence: 99%

Enhancing Machine Learning Algorithms using GPT Embeddings for Binary Classification

SATHVIK¹

2023

Preprint

View full text Add to dashboard Cite

<p>The Language Model Models (LLMs) have demonstrated their ability to process and understand natural language inputs accurately. This indicates that LLMs are capable of superior natural language processing capabilities. The GPT embeddings are words generated from the GPT backend of the ChatGPT developed by OpenAI, which can produce accurate outputs for user inputs. In this paper, we generate GPT embeddings and apply machine learning algorithms for fake news prediction and sentiment analysis. The proposed method produces remarkable results with an improvement of approximately 12.59% in accuracy compared to traditional embeddings. For fake news detection, GPT embeddings with SVM outperformed LSTM with Glove embeddings. We evaluated 10 machine learning models using 4 versions of GPT embeddings, namely Ada, Babbage, Curie, and Davinci. The sentiment analysis execution resulted in an impressive accuracy of 98.6%. We made our embeddings publicly available for both datasets. We believe that this is a valuable contribution since generating such embeddings requires access to GPT, which is not freely available to researchers.</p>

show abstract

A Novel Ensemble Learning Approach for Stock Market Prediction Based on Sentiment Analysis and the Sliding Window Method

Cited by 15 publications

References 58 publications

Inducing AI-powered chatbot use for customer purchase: the role of information value and innovative technology

Inducing AI-powered chatbot use for customer purchase: the role of information value and innovative technology

Predicting accounting fraud using imbalanced ensemble learning classifiers – evidence from China

Enhancing Machine Learning Algorithms using GPT Embeddings for Binary Classification

Contact Info

Product

Resources

About