Artificial intelligence and consumer behavior: From predictive to generative AI

Journal of Business Research, Journal Year: 2024, Volume and Issue: 180, P. 114720 - 114720

Published: May 23, 2024

Language: Английский

---

Prompt Engineering or Fine-Tuning? A Case Study on Phishing Detection with Large Language Models

Machine Learning and Knowledge Extraction, Journal Year: 2024, Volume and Issue: 6(1), P. 367 - 384

Published: Feb. 6, 2024

Large Language Models (LLMs) are reshaping the landscape of Machine Learning (ML) application development. The emergence versatile LLMs capable undertaking a wide array tasks has reduced necessity for intensive human involvement in training and maintaining ML models. Despite these advancements, pivotal question emerges: can generalized models negate need task-specific models? This study addresses this by comparing effectiveness detecting phishing URLs when utilized with prompt-engineering techniques versus fine-tuned. Notably, we explore multiple strategies URL detection apply them to two chat models, GPT-3.5-turbo Claude 2. In context, maximum result achieved was an F1-score 92.74% using test set 1000 samples. Following this, fine-tune range base LLMs, including GPT-2, Bloom, Baby LLaMA, DistilGPT-2—all primarily developed text generation—exclusively detection. fine-tuning approach culminated peak performance, achieving 97.29% AUC 99.56% on same set, thereby outperforming existing state-of-the-art methods. These results highlight that while harnessed through prompt engineering expedite development processes, decent they not as effective dedicated, LLMs.

Language: Английский

---

Using large language models to generate silicon samples in consumer and marketing research: Challenges, opportunities, and guidelines

Psychology and Marketing, Journal Year: 2024, Volume and Issue: 41(6), P. 1254 - 1270

Published: Feb. 10, 2024

Abstract Should consumer researchers employ silicon samples and artificially generated data based on large language models, such as GPT, to mimic human respondents' behavior? In this paper, we review recent research that has compared result patterns from samples, finding results vary considerably across different domains. Based these results, present specific recommendations for sample use in marketing research. We argue hold particular promise upstream parts of the process qualitative pretesting pilot studies, where collect external information safeguard follow‐up design choices. also provide a critical assessment using main studies. Finally, discuss ethical issues future avenues.

Language: Английский

---

A Manager and an AI Walk into a Bar: Does ChatGPT Make Biased Decisions Like We Do?

SSRN Electronic Journal, Journal Year: 2023, Volume and Issue: unknown

Published: Jan. 1, 2023

Large language models (LLMs) such as ChatGPT have garnered global attention recently, with a promise to disrupt and revolutionize business operations. As managers rely more on artificial intelligence (AI) technology, there is an urgent need understand whether are systematic biases in AI decision-making since they trained human data feedback, both may be highly biased. This paper tests broad range of behavioral commonly found humans that especially relevant operations management. We although can much less biased accurate than problems explicit mathematical/probabilistic natures, it also exhibits many possess, when the complicated, ambiguous, implicit. It suffer from conjunction bias probability weighting. Its preference influenced by framing, salience anticipated regret, choice reference. struggles process ambiguous information evaluates risks differently humans. produce responses similar heuristics employed humans, prone confirmation bias. To make these issues worse, overconfident. Our research characterizes ChatGPT's behaviors showcases for researchers businesses consider potentialAI developing employing

Language: Английский

---

Consumer reactions to chatbot versus human service: An investigation in the role of outcome valence and perceived empathy

Journal of Retailing and Consumer Services, Journal Year: 2024, Volume and Issue: 79, P. 103847 - 103847

Published: April 9, 2024

Language: Английский

---

The Illusion of Artificial Inclusion

Published: May 11, 2024

Human participants play a central role in the development of modern artificial intelligence (AI) technology, psychological science, and user research. Recent advances generative AI have attracted growing interest to possibility replacing human these domains with surrogates. We survey several such "substitution proposals" better understand arguments for against substituting AI. Our scoping review indicates that recent wave proposals is motivated by goals as reducing costs research work increasing diversity collected data. However, ignore ultimately conflict foundational values participants: representation, inclusion, understanding. This paper critically examines principles underlying participation help chart out paths future truly centers empowers participants.

Language: Английский

---

Integrating Self-Attention Mechanisms For Contextually Relevant Information In Product Management

International Journal of Computational and Experimental Science and Engineering, Journal Year: 2024, Volume and Issue: 10(4)

Published: Dec. 11, 2024

GPT-Product is an innovative AI solution that aims to transform product management and development by using sophisticated natural language processing (NLP) abilities. Building on Transformer architecture, frameworks like as BERT, GPT, T5 have greatly enhanced applications, thereby allowing more efficient chatbots, translation services, content generating tools, so on. utilises the advanced GPT-3.5 architecture provide full solutions for market evaluation, interpretation of client input, automated development. This enhances decision-making processes. self-attention mechanism model precise contextually appropriate information, enabling effective lifetime. uses deep learning optimise processes, decrease time-to-market, enhance quality. It positions itself essential tool firms striving maintain competitiveness in a rapidly changing industry.

Language: Английский

---

Traditional vs. AI-generated brand personalities: Impact on brand preference and purchase intention

Journal of Retailing and Consumer Services, Journal Year: 2024, Volume and Issue: 81, P. 104009 - 104009

Published: July 30, 2024

Language: Английский

---

A literature review of artificial intelligence research in business and management using machine learning and ChatGPT

Data and Information Management, Journal Year: 2024, Volume and Issue: 8(3), P. 100076 - 100076

Published: June 20, 2024

This paper investigates applying AI models and topic modelling techniques to enhance computational literature reviews in business, management, information systems. The study highlights the significance of impactful journals emphasises need for interdisciplinary transdisciplinary research, especially addressing AI's ethical regulatory challenges. We demonstrate effectiveness combining machine learning ChatGPT review process. Machine is used identify research topics, assists researchers labelling generating content, improving efficiency academic writing. By leveraging ChatGPT, we uncover label topics within literature, shedding light on thematic structure content field, allowing meaningful insights, gaps, highlight rapidly expanding areas. Additionally, contribute process by introducing a methodology that identifies papers, helping bridge gap between traditional reviews.

Language: Английский

---

Consumer segmentation with large language models

Journal of Retailing and Consumer Services, Journal Year: 2024, Volume and Issue: 82, P. 104078 - 104078

Published: Sept. 9, 2024

Language: Английский

---