We measure investors' short- and long-term stock-return expectations using both options and survey data. These expectations at different horizons reveal what investors think their own short-term expectations will be in the future, or forward return expectations. While contemporaneous short-term...

We propose a new methodology to build portfolios that hedge the economic and financial risks from climate change. Our quantity-based approach exploits information on how mutual fund managers trade in response to idiosyncratic changes in their climate risk beliefs. We exploit two types of...

We introduce artificial intelligence pricing theory (AIPT). In contrast with the APT's foundational assumption of a low dimensional factor structure in returns, the AIPT conjectures that returns are driven by a large number of factors. We first verify this conjecture empirically and show that...

We study how the social transmission of public news influences investors' beliefs and securities markets. Using an extensive dataset to measure investor social networks, we find that earnings announcements from firms in higher-centrality locations generate stronger immediate price and trading...

We study sources and implications of undiversified portfolios in a production-based asset pricing model with financial frictions. Households take concentrated positions in a single firm exposed to idiosyncratic shocks because managerial effort requires equity stakes, and because investors gain...

All of asset-pricing theory currently stems from one key assumption: price equals expected discounted payoff. And much of what we think we know about discount rates comes from studying a particular kind of expected payoff: the earnings forecasts in analyst reports. Researchers typically access...

The core statistical technology in artificial intelligence is the large-scale transformer network. We propose a new asset pricing model that implants a transformer in the stochastic discount factor. This structure leverages conditional pricing information via cross-asset information sharing and...

We investigate the economic consequences of statistical learning for arbitrage pricing in a high-dimensional setting. Arbitrageurs learn about alphas from historical data. When alphas are weak and rare, estimation errors hinder arbitrageurs--even those employing optimal machine learning...

Savings increasingly flow to low-cost index funds, which simply buy and hold the stocks in a major index, such as the S&P 500. Increased indexing impedes incorporation of idiosyncratic information into stock prices. We limit endogeneity bias by showing that exogenous idiosyncratic currency...

We investigate how information processing frictions contribute to household suboptimal saving and investment behavior. We find that 60% of open accounts in college 529 savings plans are invested suboptimally due to high expenses and tax inefficiency. Such investments yield an expected loss of 9%...