Finding Alphas. Igor Tulchinsky

pursuit for individuals who are undertaking college education as well as those who are ambitious and highly interested in breaking into the financial industry.

      Qualified candidates are those highly quantitative individuals who typically come from STEM (Science, Technology, Engineering, or Mathematics) programs. Actual majors and expertise vary and may include Statistics, Financial Engineering, Mathematics, Computer Science, Finance, Physics, or other various STEM programs.

      You can find more details on WebSim™ in Part IV of this book. Full Research Consultant program information is also available at WebSim's™ official website.

      PART I

      Introduction

      1

      Introduction to Alpha Design

      By Igor Tulchinsky

      An alpha is a combination of mathematical expressions, computer source code, and configuration parameters that can be used, in combination with historical data, to make predictions about future movements of various financial instruments. An alpha is also a forecast of the return on each of the financial securities. An alpha is also a fundamentally based opinion. The three definitions are really equivalent. Alphas definitely exist, and we design and trade them. This is because even if markets are near-efficient, something has to make them so. Traders execute alpha signals, whether algorithmic, or fundamental. Such activity moves prices, pushing them towards efficiency point.

      HOW ARE ALPHAS REPRESENTED?

      An alpha can be represented as a matrix of securities and positions indexed by time. The value of the matrix corresponds to positions in that particular stock on that particular day. Positions in stock change daily; the daily changes are traded in the securities market. The alpha produces returns, and returns have variability. The ratio of return to standard deviation (variability) of the returns is the information ratio of the alpha. It so happens that the information ratio of the alpha is maximized when alpha stock positions are proportional to the forecasted return of that stock.

Expressions and Programs

      Alphas can be represented by expressions consisting of variables or programs. Such expressions, or programs, are equivalent to each other, meaning one can always be converted to the other.

      HOW DOES ONE DESIGN AN ALPHA BASED ON DATA?

      It is simple. A price action is a response to some world event. This event is reflected in the data. If the data never changes then there is no alpha. Thus, it is changes in the data that have the information. A change in information should produce a change in the alpha.

Changes may be characterized in many ways as can be seen in Table 1.1.

Table 1.1 Expression of changes

All alpha design is the intelligent search of the space for all possible changes. An expression should express a hypothesis. Examples of this can be seen in Table 1.2.

Table 1.2 Expressions expressed as a hypothesis

      QUALITY OF AN ALPHA

      An alpha is considered one of good quality when:

      ● The idea and expression is simple.

      ● The expression/code is elegant.

      ● It has good in-sample Sharpe.

      ● It is not sensitive to small changes in data and parameters.

      ● It works in multiple universes.

      ● It works in different regions.

      ● Its profit hits a recent new high.

      ALGORITHM FOR FINDING ALPHAS

      Repeat the below steps forever:

      ● Look at the variables in the data.

      ● Get an idea of the change you want to model.

      ● Come up with a mathematical expression that translates this change into stock position.

      ● Test the expression.

      ● If the result is favorable, submit the alpha.

      2

      Alpha Genesis – The Life-Cycle of a Quantitative Model of Financial Price Prediction

      By Geoffrey Lauprete

      An alpha is a model that predicts the prices of financial instruments. And while the idea of modeling the markets and predicting prices was not new back in the 1980s and 1990s, it was during that era that cheap computing power became a reality, making possible both (1) computational modeling on Wall Street trading desks, and (2) the generation and collection of data at a rate that is still growing exponentially as of the writing of this chapter. As computers and systematic data collection became ubiquitous, the need for innovative modeling techniques that could use these newly-created data became one of the drivers of the migration of PhDs to Wall Street. Finally, it was in this climate of technology evolution and exponential data production that the quantitative trading industry was born.

      BACKGROUND

      Quantitative trading and alpha research took off at the same time that cheap computational power became available on Wall Street. Alphas are predictions that are used as inputs in quantitative trading. Another way of putting it is to say that quantitative trading is the monetization of the alphas. Note that an alpha, as a form of prediction model, is not the same thing as a pure arbitrage. Sometimes the term statistical arbitrage is used to describe quantitative trading that exploits alphas.

      Note that one could debate whether alphas ought to exist at all – some of the arguments for and against the existence of alphas can be made as part of an “efficient market hypothesis.” The financial economics academic literature tackles this problem exhaustively, qualifying the markets and the nature of information flow, and deriving conclusions based on various assumptions on the markets, the market participants and their level of rationality, and how the participants interact and process information.

      That said, from a simple intuitive perspective, it makes sense that a very complex system such as the markets would exhibit some level of predictability. Whether these predictions can form the basis of exploitable opportunities is the argument that the quantitative trading industry is making every day, with more or less success.

      CHALLENGES

      Even if one can make an argument in favor of the existence of alphas under various stylized assumptions, the details of prediction in the real world are messy. A prediction with low accuracy, or a prediction that estimates a weak price change, may not be interesting from a practitioner’s perspective. The markets are an aggregate of people’s intentions, affected by changing technology, macro-economic reality, regulations, and wealth – which makes the business of prediction more challenging than meets the eye. Thus, to model the markets, one needs a strong understanding of the exogenous variables that affect the prices of financial instruments.

      THE LIFE-CYCLE OF ALPHAS

      A fundamental law of the markets is that any potentially profitable strategy attracts attention and attracts capital. Since the markets are a finite size, when more capital chases a strategy or employs a particular alpha, this implies that the fixed-sized pie that constituted the original opportunity needs to be sliced into multiple thinner slices. The end result is that, while alphas are born from the interaction of market participants, when they are (1) strong enough, (2) old enough, and (3) consistent enough to be statistically validated and provide the basis for profitable trading strategies, they will begin to attract capital. This capital flow will ensure that the alpha will shrink and become more volatile, until there is so much capital chasing the idea that it will stop working. However, this process will affect the markets