We provide novel evidence suggestive of insider trading through concealed relationships identified using information from over 100,000 Facebook profiles and their 35 million friends. Focusing on connections between fund managers and firm officers, we demonstrate that hidden ties are linked to substantial abnormal returns averaging 135 basis points per month (exceeding 16% alpha annually, t -stat = 3.54) across the universe of mutual funds and public firms. These hidden ties emerge as the most powerful predictor of future stock returns among documented network characteristics, with predictive power increasing over time through the present day. The premium associated with such connections arises not from endogenous selection or familiarity bias; instead, fund managers exhibit specific timing ability in deciding when to hold (or avoid) stocks of firm officers linked through hidden ties. The value of trading information rises with the degree of concealment and is concentrated around earnings and M&A events. The premium is absent in index funds, where strategic stock selection and timing are infeasible. Our findings on the value of hidden ties remain robust across industries, investment styles, time periods, and firm types.

We show that the introduction of a leverage constraint improves the practical implementation of characteristics-based portfolios. The addition of the constraint leads to significantly lower transaction costs, to a reduction of negative portfolio weights, and to a decrease in volatility and misspecification risk. Furthermore, it allows investors to implement any desired level of leverage. In this study, we include 12 characteristics, thereby extending the classical size, book-to-market and momentum paradigm. We report several key indicators such as the proportion of negative weights, Sharpe ratio, volatility, transaction costs, the transaction cost-adjusted certainty equivalent returns, and the Herfindahl–Hirschman index. Analyzing the sensitivity of these key indicators to the choice of multiple combinations of the 12 characteristics, to risk aversion, and to estimation sample size, we show that constrained policies are much less sensitive to these parameters than their unconstrained counterparts. Finally, for quadratic utility, we derive a semi-closed analytical form for the portfolio weights. Overall, we provide a comprehensive extension of characteristics-based portfolio choice and contribute to a better understanding and implementation of the allocation process.