|
on Financial Markets |
| By: | Qianan Wang; Zen Chen |
| Abstract: | The rapid expansion of artificial intelligence (AI) investment has revived a recurrent question in financial economics: are AI-related assets experiencing a bubble, or is the market capitaliz- ing a durable general-purpose technology? This paper develops a hybrid review and diagnostic framework for evaluating whether AI is in an ongoing financial bubble as of May 2026. The analysis begins from asset-pricing foundations in state prices, stochastic discount factors, martingale valuation, and pricing kernels, then connects these foundations to rational bubbles, behavioral bubbles, technology manias, and modern econometric bubble-detection methods. Current evidence shows both genuine fundamentals and bubble-like fragilities. On the fundamental side, realized revenue growth, enterprise adoption, and productivity evidence support a nontrivial share of AI valuations. On the fragile side, capital expenditure has accelerated faster than observed monetization in some layers, private- market valuations are concentrated in a small number of firms, and investor narratives often capitalize future productivity gains before they have appeared in cash flows. The paper proposes a five-pillar diagnostic framework that combines fundamental valuation, residual-exuberance tests, SADF/GSADF explosive-root procedures, LPPL/HLPPL price-pattern diagnostics, sen- timent and issuance measures, and capex-payback analysis. The central conclusion is that AI is best understood as a real technological revolution with localized bubble dynamics rather than as either a pure speculative mania or a bubble-free productivity miracle. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.01575 |
| By: | Matteo Aquilina; Peter Cincinelli; Giovanni Urga |
| Abstract: | We investigate the systemic risk contribution of 3, 500 Money Market Funds (MMFs) in normal periods and during asset price bubbles in the US from January 2004 to December 2022. Using state-of-the-art statistical techniques for bubble detection and granular fund-level data, we show that MMF characteristics significantly influence systemic risk. Large MMFs and government MMFs, which invest exclusively in US Treasury securities, are associated with reduced systemic risk, while prime MMFs contribute to higher systemic risk. MMFs denominated in US dollars but domiciled offshore exhibit no significant differences from their US-domiciled counterparts. |
| Keywords: | financial crises, financial bubbles, backward supremum augmented Dickey-Fuller test, systemic risk measures, panel data |
| JEL: | C23 G21 G15 |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:bis:biswps:1358 |
| By: | Anneke Kosse; Tara Rice; Fabian Schär; Takeshi Shirakami; Jirapat Siridhasanakul |
| Abstract: | Stablecoin transfers are often interpreted as payments. On programmable blockchains, however, they are frequently embedded in atomically executed transaction bundles that combine trading, lending, arbitrage, liquidity provision, and settlement. We show that ignoring this structure materially distorts the interpretation of stablecoin activity. Using 593 million event logs from 141 million Ethereum transactions involving three major U.S. dollar stablecoins, we develop a replicable framework to measure transaction complexity from archive node data, public contract labels, and event signatures. The analysis combines measures of token and contract co-usage, action type, computational complexity, urgency, and timing. Two results emerge. First, complexity is a first-order feature of stablecoin activity: nearly 60 percent of transfer events occur within complex transactions. Second, the three stable coins are not used interchangeably: their use differs systematically across transaction structures, urgency, and timing, consistent with distinct institutional designs and economic functions. Analyses that treat transfers as standalone payments therefore risk misclassifying a large share of on-chain stablecoin use, with implications for empirical measurement, market monitoring, and policy. |
| Keywords: | blockchain, payments, policy and regulation, stablecoins, transaction complexity |
| JEL: | E42 O33 G28 C81 G23 |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:bis:biswps:1359 |
| By: | Nicolas Pasquier |
| Abstract: | Traditional firms competing in a primary market may expand into a secondary market that generates user data and enhances the quality of the primary product. This paper examines how competition between such rival ecosystems affects market outcomes and welfare. Using a Hotelling framework with two symmetric ecosystems that each offer a primary product and a secondary data-rich product, I show that the size of the secondary market is key. When the secondary market is small, ecosystems invest less in quality than in a benchmark with only a primary market and earn higher profits at the expense of consumers. As the secondary market grows, quality investment rises and the welfare ranking can reverse. I further show that expansion into a secondary market need not create a trade-off between profits and consumer surplus: when the ecosystems’ secondary products are sufficiently differentiated, both profits and consumer surplus can exceed their benchmark levels. These findings inform policy debates on digital adoption, market structure, and ecosystem regulation. |
| Keywords: | Competing Ecosystems, Quality Investment, Data-Driven Quality |
| JEL: | L13 L51 D43 O31 Q16 |
| Date: | 2025–06 |
| URL: | https://d.repec.org/n?u=RePEc:gbl:wpaper:2026-03 |
| By: | Sung Je Byun; Johnathan Loudis; Lawrence D.W. Schmidt |
| Abstract: | We construct a Broad Market Factor (BMF), which is a proxy for the value-weighted equity return on all firms in the US economy (public and private). The BMF differs from the standard Value-weighted Market Factor (VMF), which reflects the value-weighted equity return on public firms. We define the difference between the VMF and the BMF to be the Idiosyncratic Financial Factor (IFF). The IFF carries no risk premium and is uncorrelated with all macroeconomic proxies for investor marginal utility we consider. CAPM betas and, consequently, discount rates are underestimated when measured with respect to the VMF compared to the BMF for most portfolios. Size factors become redundant and the size anomaly is resolved when the VMF is replaced by the BMF in standard factor models. The intertemporal risk-return relation is substantially stronger when one replaces the VMF with the BMF. The unifying explanation for these results is that the IFF adds unpriced risk to the VMF, distorting both cross-sectional and time-series estimates of exposure to priced market risk. |
| JEL: | C15 C58 G12 G17 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35243 |
| By: | Yong Zhang; Xinxiao Wu; Yunde Jia; Che Sun |
| Abstract: | Accurate stock price forecasting has consistently remained a pivotal yet challenging FinTech task that underpins quantitative trading and investment decision making. Recent efforts have been dedicated to modeling various complex relationships among stocks in the stock market toward more reliable stock price forecasting.These methods depend heavily on strong static prior assumptions by modeling either temporal dependencies within individual stocks or spatial dependencies across different stocks based on predefined structures, while the complex market dynamics that drive stock price movements remain unexplored. To alleviate this issue, we propose a novel game-theoretic modeling method that captures heterogeneous investor interactions for stock price forecasting. The core idea is to embed game-theoretic mechanisms into the heterogeneous graph structure to finely model the dynamic strategic interactions among heterogeneous investors with respect to target stocks. Additionally, temporal positional encoding is adopted to reflect the differentiated influences of each game event at different time steps within the time window on future stock price movements. Leveraging heterogeneous graph networks, we proxy the intricate dynamics of the stock market through investor games and enable real-time information propagation and node updates among all nodes. Extensive experiments conducted on two real-world benchmark dataset demonstrate that our method effectively outperforms state-of-the-art stock price forecasting methods. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.23953 |
| By: | Muhammad Aldy Hassan; Hokky Situngkir |
| Abstract: | The collective movement of stock prices harbors complex interdependencies that are conventionally simplified only through a linear lens. This paper explores computed structural network representations in the Indonesian capital market by testing the limits of Pearson correlation and Mutual Information (MI) in unveiling the spectral dynamics of the market. Across 2, 328 rolling observation windows from 2015 to 2025, we examine 24 methodological configurations that combine three dependency estimators (Pearson, MI adaptive binning, and MI-kNN), two graph filtering schemes (Minimum Spanning Tree/MST and Planar Maximally Filtered Graph/PMFG), and four community decoders. The empirical results unveil a fundamental reality: topological richness does not always resonate with sectoral classification precision. The Pearson, MST, and Infomap configuration is shown to remain the most robust foundation for recovering conventional sectoral taxonomy. Nevertheless, when deeper observation demands the exposition of local structures and the weave of heterogeneous communities, the architectural relaxation through PMFG demonstrates its superiority. In the realm of residual information detection, MI adaptive binning appears far more proportional than kNN; histogram-based regularization successfully tames empirical noise without sweeping away traces of non-linear dependency. Ultimately, the synergy of MI and PMFG is not positioned to dethrone the dominance of linear correlation, but rather to provide an essential analytical lens for excavating hidden economic sub-structures -- such as the cohesion of commodity regimes -- that have long transcended the rigid boundaries of the market's formal sectors. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.07450 |
| By: | Mindy L. Mallory |
| Abstract: | This paper estimates the carry embedded in listed IBIT options and compares it with the carry embedded in matched CME bitcoin futures. Put-call parity recovers an implied forward on the ETF; BlackRock's daily holdings file maps each ETF share into bitcoin units; and CME futures prices and BRRNY, a U.S. close bitcoin reference rate, provide the corresponding futures-market carry. The difference in carry implied by these two products is consistent with frictions that limit cross-margining between spot bitcoin or ETF exposure and CME futures. In the selected-strike IBIT sample of 386 date-bucket observations, the mean wedge is 2.58 percent and the median wedge is 2.52 percent, both measured in annual percentage points. The result is consistent with segmented collateral and margin systems limiting arbitrage between regulated bitcoin-exposure venues. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2605.29309 |
| By: | Shuang Chen; Clemens Sialm; David X. Xu |
| Abstract: | We examine the growth and performance of AI-driven investing. Using investment advisers' regulatory disclosures, labor market data, and fund strategy descriptions, we document that AI-driven investing has grown steadily since the early 2010s and is concentrated among hedge funds. AI hedge funds outperformed non-AI hedge funds in the early years, but this outperformance declined over time, even among early adopters. Contrary to concerns about AI-driven strategy homogeneity, AI hedge funds exhibit lower return comovement than non-AI peers. Our findings highlight both the alpha-generating potential and the limitations of AI as a source of investment performance. |
| JEL: | G11 G23 G24 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35273 |
| By: | Kenneth R. Ahern |
| Abstract: | This paper shows that the industrial composition of a city's local economy affects its municipal borrowing costs. In a panel of 1, 177 U.S. cities from 2005 to 2022, greater sectoral concentration magnifies default risk and raises bond spreads, especially for cities dominated by industries associated with low property values. Instrumental variables exploiting national sector-employment trends and regional house-price variation support a causal interpretation. A calibrated model of city default suggests that the observed spread effect understates the gross risk created by concentration, because higher concentration can generate agglomeration benefits that reduce spreads, especially for high-property-value cities. |
| JEL: | G12 H74 R51 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35228 |
| By: | Xinzhao Xie; Bopei Nie; Kuo-Ping Chang |
| Abstract: | This paper has used European put option to construct the p-index risk measure to evaluate the performance of different investment strategies in China's SSE 50 index and the US SP500 index during 2018-2023. The p-index measures the insurance fee for each insured dollar to guarantee that the asset achieves at least a delta rate of return on a specified future date. It is found that with the fair price strategy, one-week and one-month holding periods can earn more, and among seven economic sectors, materials sector stocks generated highest annualized rates of return: 11.04% (one-week period), 11.93% (two-week period) and 10.18% (one-month period). With momentum and contrarian strategies of one-week holding period, the p-ratio-efficient-contrarian strategy produced the highest annualized rate of return (9.97%), followed by the p-index-inefficient-momentum strategy (9.01%) and the p-index-efficient-contrarian strategy (6.48%), the MCIRS method employing the p-index consistently delivered higher returns than its beta-based approach, and efficient (outperforming) stocks failed to sustain their momentum while inefficient (underperforming) stocks exhibited no mean reversion. It is also found that the p-index-efficient-contrarian strategy outperformed in low-sentiment (low-volume) regimes, while the p-index-inefficient-momentum strategy outperformed during high-sentiment (high-volume) periods. For the five hundred stocks of the US S&P 500 index during 2018-2023, it is found that efficient stocks sustained their momentum while inefficient stocks exhibited mean reversion. The p-index-efficient-momentum strategy produced the highest annualized rate of return (3.69%), followed by the p-ratio-inefficient-contrarian strategy (3.67%) and the beta-efficient-momentum strategy (3.48%). |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.08569 |
| By: | Dora Xia; Omar Zulaica |
| Abstract: | We propose a framework for constructing fixed-income portfolios of sovereign bonds that integrates financial and environmental considerations. Central to our approach is the introduction of carbon returns, a concept analogous to financial returns, modeled as random variables to capture the inherent uncertainty of future carbon emissions. Based on the financial and carbon return profiles of individual countries' sovereign bonds, we employ an algorithm inspired by Hierarchical Risk Parity (HRP) to construct portfolios that balance each country's contribution to the portfolio's tail risk, as measured by expected shortfall, of financial and carbon returns. Focusing on developed market sovereign bonds, our results demonstrate that it is possible to design portfolios that effectively align decarbonization objectives with financial performance, both in-sample and out-of-sample, while accommodating diverse investor preferences. |
| Keywords: | carbon footprints, sovereign debt, portfolio optimization, risk parity |
| JEL: | G11 G28 Q54 Q56 |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:bis:biswps:1362 |
| By: | Andrei Bysik; Robert \'Slepaczuk |
| Abstract: | This paper investigates whether machine learning forecasts of hourly BTC-USDT returns can be converted into economically meaningful trading performance after transaction costs. Using approximately 70, 000 hourly observations from 2018-2026, XGBoost, LSTM, and iTransformer are evaluated in a 27-fold walk-forward protocol. All three models produce positive gross trading performance in selected configurations, but naive sign-based strategies fail once transaction costs of ten basis points are imposed. A cost-aware execution filter, which prevents trades only when the forecast magnitude exceeds a transaction-cost-based threshold, sharply reduces turnover and restores profitability in selected configurations. The strongest long-only XGBoost strategy produces annualised returns above 65% with a Sharpe ratio above one. Additional tests show that technical indicators improve performance in selected cases, EGARCH-derived features do not provide uniformly robust gains, and XGBoost is descriptively stronger than the neural alternatives, although bootstrap evidence does not support formal statistical dominance. Loss-function and model-selection effects are secondary and statistically fragile. The results show that the main obstacle in hourly cryptocurrency trading is not only weak predictability, but also the way forecasts are converted into trades. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.00060 |
| By: | Aoxin Zhang; Yuhan Cheng; Kwanting Leung |
| Abstract: | Benchmarking forecasting architectures for daily equity portfolios is not just a prediction exercise. It also asks which model remains usable after preferences, costs, and portfolio constraints are imposed. We build a CRSP daily-stock benchmark for 15 deep and statistical time-series architectures over 2018--2024. The protocol combines common-window decile portfolios, stochastic multi-criteria acceptability analysis, a deployment-adjusted acceptability index, and a constrained quadratic portfolio layer with capacity, beta, industry, risk, leverage, and turnover controls. The index starts from the SMAA rank-acceptability distribution and downweights models whose criteria-level wins produce high portfolio regret; its Gibbs form is characterized as an entropic update from the SMAA prior. Empirically, no architecture dominates the raw benchmark: TransEnc-8 has the largest rank-1 acceptability, 0.352, and no model exceeds about 0.36. Rankings vary with preferences, market state, feature universe, and transaction costs. In the promoted five-model constrained-portfolio comparison, TransEnc-8 is selected throughout, while return-oriented raw rankings can favor TS-RIDGE. Broad-universe decile signals can survive costs, but the baseline constrained-QP net Sharpe at 20 bps is negative for every promoted model. The benchmark supports model selection and diagnosis rather than a standalone trading-strategy claim. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.09420 |
| By: | Oliver Hellum; Theis I. Jensen; Bryan T. Kelly; Semyon Malamud |
| Abstract: | The literature has long wrestled with the practical usefulness of Modern Portfolio Theory (MPT), and extensive evidence shows its performance decreases rapidly with the number of assets (N ). We present several new and counterintuitive facts about MPT. Most importantly, the performance of MPT in fact increases with N once the number of assets exceeds the number of training observations (T ). This finding holds in a variety of settings: in conjunction with popular portfolio regularization methods, in a variety of asset universes, and when T is large or small. |
| JEL: | C49 G1 G11 |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:nbr:nberwo:35246 |
| By: | Xinyue Fang; Robert \'Slepaczuk |
| Abstract: | This study investigates whether regime-dependent volatility forecasting and machine-learning-based return prediction can be jointly integrated to improve both statistical forecasting performance and economic strategy outcomes in equity markets. Using high-frequency CSI 300 Index data from 2005 to 2023, a sequential twostage framework is developed. In the first stage, realized volatility is modeled using regime-augmented HARQ specifications combined with Markov-switching GJR-GARCH filtering to capture long-memory dynamics, asymmetry, and structural market regimes. In the second stage, volatility forecasts, regime indicators, and return-related predictors are incorporated into an XGBoost return-prediction model estimated through a strictly walk-forward out-of-sample procedure. The empirical results demonstrate that regime-aware volatility forecasting consistently outperforms baseline HARQ models across forecast evaluation metrics and is generally supported by formal forecast comparison tests. In contrast, return predictability remains weak, state-dependent, and concentrated primarily in low-volatility regimes. Although naive predictive trading strategies generally fail after accounting for realistic transaction costs, carefully designed implementations incorporating volatility scaling, low-volatility gating, threshold calibration, and turnover controls can improve defensive economic performance. The findings suggest that the practical value of predictive systems in financial markets may depend less on generating strong unconditional return forecasts and more on transforming weak state-dependent signals into economically robust portfolio allocation rules. Overall, the study contributes by integrating econometric volatility modeling, regime classification, machine-learning return prediction, and implementation realism within a unified framework. |
| Date: | 2026–06 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.09478 |
| By: | Carlos Baquero |
| Abstract: | Bitcoin price prediction has attracted hundreds of academic papers and continuous social media debate, yet the field lacks consensus on even basic questions: can any model beat a naive "today's price" baseline at horizons of one to six months? We survey the peer-reviewed landscape, categorize papers by evaluation methodology, and contrast academic findings with informal but substantive discourse on X/Twitter. The picture that emerges is sobering. At short-to-medium horizons, no peer-reviewed study has shown robust superiority over the naive baseline across multiple market regimes. Daily predictability is real but does not extend to hourly or monthly horizons, and may not survive transaction costs. The stock-to-flow model has failed formal out-of-sample testing, and Metcalfe's Law valuations have been challenged as spurious. The Bitcoin price power law, while empirically compelling, has not been subjected to formal distributional tests. Meanwhile, social media practitioners raise valid statistical critiques -- ordinary least squares (OLS) violations, backtest overfitting, spurious regressions -- that the academic literature has not formalized. We identify open research directions and propose concrete methodological standards for future work -- walk-forward evaluation, multi-regime holdout windows, naive baseline comparison, inclusion of zero in hyperparameter grids, and Diebold-Mariano significance testing -- arguing that the field's primary need is not more models but better evaluation. |
| Date: | 2026–05 |
| URL: | https://d.repec.org/n?u=RePEc:arx:papers:2606.00071 |