The integration of generative AI (GAI) into the financial sector has brought about significant advancements, offering new solutions for various financial tasks. This review paper provides a comprehensive examination of recent trends and developments at the intersection of GAI and finance. By utilizing an advanced topic modeling method, BERTopic, we systematically categorize and analyze existing research to uncover predominant themes and emerging areas of interest. Our findings reveal the transformative impact of finance-specific large language models (LLMs), the innovative use of generative adversarial networks (GANs) in synthetic financial data generation, and the pressing necessity of a new regulatory framework to govern the use of GAI in the finance sector. This paper aims to provide researchers and practitioners with a structured overview of the current landscape of GAI in finance, offering insights into both the opportunities and challenges presented by these advanced technologies.
The unique short-sales restrictions present in the Hong Kong stock market, where a list of designated securities that can be sold short is revised from time to time, provide valuable data for examining the effects of short-sales constraints on market efficiency, especially efficiency in price discovery. By analyzing the cumulative abnormal returns around the lifting and reinstatement of short-sales restrictions, we find that short-sales constraints tend to cause stock overvaluation and that the overvaluation effect is more dramatic for individual stocks where wider dispersion of investor opinions exist. The evidence suggests that eliminating short-sales restrictions helps improve the efficiency of price discovery, which is consistent with Miller (1977)'s intuition. We also find that when short sales are allowed, individual stock return exhibits higher volatility and less positive skewness.
This study builds upon previous research by exploring the deeper relationship between the thematic and emotional content of top-charting music lyrics and stock price movements. Focusing on the Japan Nikkei Stock Average, this chapter investigate how thematic and emotional expressions in popular music lyrics correlate with stock market returns. Utilizing a Stream-Weighted Music Lyrics (SWML) vector as input for a Long Short-Term Memory (LSTM) model, this study forecast stock returns based on the semantic content of lyrics. This approach offers potential advancements in both theoretical understanding and practical applications for market participants. The findings make a significant contribution to the field of behavioral finance by introducing music consumption as a valuable, unconventional indicator of investor psychological states and market dynamics. The study highlights the potential of integrating psychological signals into investment strategies, offering a fresh perspective on how non-traditional data sources can enhance market analysis and decision-making.
We examine whether aggregate “music mood” derived from globally popular songs can help forecast primary equity issuance. We build a Friday-anchored weekly panel that merges SEC EDGAR counts of priced Initial Public Offerings (IPOs) with features from the Spotify Daily Top 200 (audio descriptors such as valence, energy, danceability, tempo, loudness, etc.) and Genius-scraped lyrics. We extract lyric sentiment by tokenizing Genius-scraped lyrics and aggregating lexicon-based affect scores (valence and arousal) into popularity-weighted weekly indices. To address sparsity and regime shifts in issuance, we train a leakage-safe Long Short-Term Memory (LSTM) network on a smoothed target—the forward 4-week sum of IPOs—and obtain next-week forecasts by dividing the predicted sum by 4. On a chronological holdout, a single LSTM with look-back K = 8 outperforms strong baselines—reducing MAE by 13.9%, RMSE by 15.9%, and mean Poisson deviance by 27.6% relative to the best baseline in each metric. Furthermore, we adopt SHapley Additive exPlanations (SHAP) to explain our LSTM model, showing that IPO persistence remains the dominant driver, but music and lyrics covariates contribute incremental and robust signal. These results suggest that aggregate music sentiment contains economically meaningful information about near-term IPO activity.
This study investigates the correlation between the audio features of top-charting music and Non-Fungible Tokens (NFT) market dynamics, presenting a novel perspective within the realm of behavioral finance. Drawing on the regulatory focus theory and existing research on music's affective influence, the authors argue that popular music, as a reflection of society's collective regulatory focus, can significantly impact trading behaviours in NFTs, an asset class known for its susceptibility to emotional drivers and speculative activity. By employing a Long Short-Term Memory (LSTM) machine learning model and permutation importance technique, the analysis demonstrates that specific musical attributes—such as danceability, loudness, and mode—exhibit predictive power over daily NFT trading volumes. The study not only provides evidence of music's capacity to signal shifts in trading behaviors, offering innovative insights into the drivers of digital asset markets, but introduces a new interdisciplinary approach focusing on the collective regulatory focus reflected in the music.
The convergence of blockchain and immersive technologies has resulted in the popularity of Metaverse platforms and their cryptocurrencies, known as Metaverse tokens. There has been little research into tokenomics in these emerging tokens. Building upon the information dissemination theory, this research examines the role of trading volume in the returns of these tokens. An empirical study was conducted using the trading volumes and returns of 197 Metaverse tokens over 12 months to derive the latent grouping structure with spectral clustering and to determine the relationships between daily returns of different token clusters through augmented vector autoregression. The results show that trading volume is a strong predictor of lead-lag patterns, which supports the speed of adjustment hypothesis. This is the first large-scale study that documented the lead-lag effect among Metaverse tokens. Unlike previous studies that focus on market capitalization, our findings suggest that trade volume contains vital information concerning cross-correlation patterns.