We apply machine-learning techniques to construct nonlinear nonparametric forecasting models of consumer credit risk. By combining customer transactions and credit bureau data from January 2005 to April 2009 for a sample of a major commercial bank's customers, we are able to construct out-of-sample forecasts that significantly improve the classification rates of credit-card-holder delinquencies and defaults, with linear regression R-squared's of forecasted/realized delinquencies of 85%. Using conservative assumptions for the costs and benefits of cutting credit lines based on machine-learning forecasts, we estimate the cost savings to range from 6% to 25% of total losses. Moreover, the time-series patterns of estimated delinquency rates from this model over the course of the recent financial crisis suggests that aggregated consumer-credit risk analytics may have important applications in forecasting systemic risk.

The quantitative aspirations of economists and financial analysts have for many years been based on the belief that it should be possible to build models of economic systems—and financial markets in particular—that are as predictive as those in physics. While this perspective has led to a number of important breakthroughs in economics, "physics envy" has also created a false sense of mathematical precision in some cases. We speculate on the origins of physics envy, and then describe an alternate perspective of economic behavior based on a new taxonomy of uncertainty. We illustrated the relevance of this taxonomy with two concrete examples: the classical harmonic oscillator with some new twists that make physics look more like economics, and a quantitative equity market-neutral strategy. We conclude by offering a new interpretation of tail events, proposing an 'uncertainty checklist' with which our taxonomy can be implemented, and considering the role that quants played in the current financial crisis.

A key result of the Capital Asset Pricing Model (CAPM) is that the market portfolio—the portfolio of all assets in which each asset's weight is proportional to its total market capitalization—lies on the mean-variance-efficient frontier, the set of portfolios having mean-variance characteristics that cannot be improved upon. Therefore, the CAPM cannot be consistent with efficient frontiers for which every frontier portfolio has at least one negative weight or short position. We call such efficient frontiers 'impossible', and show that impossible frontiers are difficult to avoid. In particular, as the number of assets, n, grows, we prove that the probability that a generically chosen frontier is impossible tends to one at a geometric rate. In fact, for one natural class of distributions, nearly one-eighth of all assets on a frontier is expected to have negative weights for every portfolio on the frontier. We also show that the expected minimum amount of shortselling across frontier portfolios grows linearly with n, and even when shortsales are constrained to some finite level, an impossible frontier remains impossible. Using daily and monthly U.S. stock returns, we document the impossibility of efficient frontiers in the data.

In response to the current financial crisis, a number of hedge funds have implemented "gates" on their funds that restrict withdrawals when the sum of redemption requests exceeds a certain percentage of the fund's total assets. To reduce the investor's risk exposures during these periods, we propose a futures overlay strategy designed to hedge out or control the common factor exposures of gated assets. By taking countervailing positions in stock, bond, currency, and commodity exposures, an investor can greatly reduce the systematic risks of their gated assets while still enjoying the benefits of manager-specific alpha. Such overlay strategies can also be used to reposition the betas of an investor's entire portfolio, effectively rebalancing asset-class exposures without having to trade the less liquid underlying assets during periods of market dislocation. To illustrate the costs and benefits of such overlay, we simulate the impact of a simple beta-hedging strategy applied to long/short equity hedge funds in the TASS database.

The value of active investment management is traditionally measured by alpha, beta, tracking error, and the Sharpe and information ratios. These are essentially static characteristics of the marginal distributions of returns at a single point in time, and do not incorporate dynamic aspects of a manager's investment process. In this paper, I propose a new measure of the value of active investment management that captures both static and dynamic contributions of a portfolio manager's decisions. The measure is based on a decomposition of a portfolio's expected return into two distinct components: a static weighted-average of the individual securities' expected returns, and the sum of covariances between returns and portfolio weights. The former component measures the portion of the manager's expected return due to static investments in the underlying securities, while the latter component captures the forecast power implicit in the manager's dynamic investment choices. This measure can be computed for long-only investments, long/short portfolios, and asset allocation rules, and is particularly relevant for hedge-fund strategies where both components are significant contributors to their expected returns, but only one should garner the high fees that hedge funds typically charge. Several analytical and empirical examples are provided to illustrate the practical relevance of these new measures.

Long-only portfolio managers and investors have acknowledged that the long-only constraint is a potentially costly drag on performance, and loosening this constraint can add value. However, the magnitude of the performance drag is difficult to measure without a proper benchmark for a 130/30 portfolio. In this paper, we provide a passive but dynamic benchmark consisting of a 'plain-vanilla' 130/30 strategy using simple factors to rank stocks and standard methods for constructing portfolios based on these rankings. Based on this strategy, we produce two types of indexes: investable and 'look ahead' indexes, in which the former uses only prior information and the latter uses realized returns to produce an upper bound on performance. We provide historical simulations of our 130/30 benchmarks that illustrate their advantages and disadvantages under various market conditions.

During the week of August 6, 2007, a number of quantitative long/short equity hedge funds experienced unprecedented losses. Based on TASS hedge-fund data and simulations of a specific long/short equity strategy, we hypothesize that the losses were initiated by the rapid "unwind" of one or more sizable quantitative equity market-neutral portfolios. Given the speed and price impact with which this occurred, it was likely the result of a forced liquidation by a multi-strategy fund or proprietary-trading desk, possibly due to a margin call or a risk reduction. These initial losses then put pressure on a broader set of long/short and long-only equity portfolios, causing further losses by triggering stop/loss and de-leveraging policies. A significant rebound of these strategies occurred on August 10th, which is also consistent with the unwind hypothesis. This dislocation was apparently caused by forces outside the long/short equity sector—in a completely unrelated set of markets and instruments—suggesting that systemic risk in the hedge-fund industry may have increased in recent years.

In contrast to traditional investments such as stocks and bonds, hedge-fund returns have more complex risk exposures that yield additional and complementary sources of risk premia. This raises the possibility of creating passive replicating portfolios or "clones" using liquid exchange-traded instruments that provide similar risk exposures at lower cost and with greater transparency. Using monthly returns data for 1,610 hedge funds in the TASS database from 1986 to 2005, we estimate linear factor models for individual hedge funds using six common factors, and measure the proportion of the funds' expected returns and volatility that are attributable to such factors. For certain hedge-fund style categories, we find that a significant fraction of both can be captured by common factors corresponding to liquid exchange-traded instruments. While the performance of linear clones is often inferior to their hedge-fund counterparts, they perform well enough to warrant serious consideration as passive, transparent, scalable, and lower-cost alternatives to hedge funds.

We derive an intertemporal capital asset pricing model with multiple assets and heterogeneous investors, and explore its implications for the behavior of trading volume and asset returns. Assets contain two types of risks: market risk and the risk of changing market conditions. We show that investors trade only in two portfolios: the market portfolio, and a hedging portfolio, which allows them to hedge the dynamic risk. This implies that trading volume of individual assets exhibit a two-factor structure, and their factor loadings depend on their weights in the hedging portfolio. This allows us to empirically identify the hedging portfolio using volume data. We then test the two properties of the hedging portfolio: its return provides the best predictor of future market returns and its return together with the return of the market portfolio are the two risk factors determining the cross-section of asset returns.

The battle between proponents of the Efficient Markets Hypothesis and champions of behavioral finance has never been more pitched, and there is little consensus as to which side is winning or what the implications are for investment management and consulting. In this article, I review the case for and against the Efficient Markets Hypothesis, and describe a new framework—the Adaptive Markets Hypothesis—in which the traditional models of modern financial economics can co-exist alongside behavioral models in an intellectually consistent manner. Based on evolutionary principles, the Adaptive Markets Hypothesis implies that the degree of market efficiency is related to environmental factors characterizing market ecology such as the number of competitors in the market, the magnitude of profit opportunities available, and the adaptability of the market participants. Many of the examples that behavioralists cite as violations of rationality that are inconsistent with market efficiency—loss aversion, overconfidence, overreaction, mental accounting, and other behavioral biases—are, in fact, consistent with an evolutionary model of individuals adapting to a changing environment via simple heuristics. Despite the qualitative nature of this new paradigm, I show that the Adaptive Markets Hypothesis yields a number of surprisingly concrete applications for both investment managers and consultants.