Category Archives: stocks

The Wisdom Of Twitter Crowds: Tweet-Based Asset-Allocation Strategy Outperforms Several Benchmarks

By Jacob Wolinsky Interesting study and finding from Andrew Lo re Twitter and FOMC: “The Wisdom of Twitter Crowds: Predicting Stock Market Reactions to FOMC Meetings via Twitter Feeds” Pablo D. Azar is a PhD student in the Department of Economics and Laboratory for Financial Engineering, Sloan School of Management, MIT. Email: pazar@mit.edu Andrew W. Lo is Charles E. and Susan T. Harris Professor and the Director of the Laboratory for Financial Engineering, Sloan School of Management, MIT. Email: alo-admin@mit.edu Abstract With the rise of social media, investors have a new tool to measure sentiment in real time. However, the nature of these sources of data raises serious questions about its quality. Since anyone on social media can participate in a conversation about markets—whether they are informed or not—it is possible that this data may have very little information about future asset prices. In this paper, we show that this is not the case by analyzing a recurring event that has a high impact on asset prices: Federal Open Market Committee (FOMC) meetings. We exploit a new dataset of tweets referencing the Federal Reserve and show that the content of tweets can be used to predict future returns, even after controlling for common asset pricing factors. To gauge the economic magnitude of these predictions, the authors construct a simple hypothetical trading strategy based on this data. They find that a tweet based asset-allocation strategy outperforms several benchmarks, including a strategy that buys and holds a market index as well as a comparable dynamic asset allocation strategy that does not use Twitter information. Investor sentiment has frequently been considered an important factor in determining asset prices. Traditionally, sentiment is measured by observing analyst estimates, survey data, news stories, and technical indicators such as put/call ratios and relative strength indicators. Two drawbacks of these indicators are that they are based on a relatively sparse subset of the population of investors and, except for technical indicators, are not measured in real time. The rise of social media allows us to overcome these drawbacks and measure the sentiment of a large number of individuals in real time. These data sources give the quantitative investor a new tool with which to construct portfolios and manage risk. However, because social media data is generated by individual users and not investment professionals, the following questions arise about the quality of this data: • Do user messages contain relevant information for asset pricing? • Can this information be inferred from more traditional sources, or is it truly new information? • Can social media data help predict future asset returns and shifts in volatility? To answer these questions, we focus on a single recurring event that reveals previously unknown information to the market: Federal Open Market Committee (FOMC) meetings. Eight times a year, the FOMC meets to determine monetary policy. The decisions made by the FOMC are highly watched by all market participants, and often have a significant impact on asset prices.1 To understand how investors on social media behave around FOMC meeting dates, we create a new dataset of tweets that cite the Federal Reserve. Using natural language processing techniques, we can assign a polarity score to each Twitter message, identifying the emotion in the text. We show that this polarity score can be used to predict the returns of the CRSP Value-Weighted Index, even when limiting ourselves to articles and tweets that are published at least 24 hours before the FOMC meeting. We use these results to construct trading strategies that bet more or less aggressively in a market index depending on Twitter sentiment. We find that portfolios using Twitter data can significantly outperform a passive buy-and-hold strategy. Click to enlarge Click to enlarge Full study below SSRN-id2756815

If All Investments Were Private

This piece is another one of my experiments, please bear with me. “Measure Twice, Cut Once” – A very intelligent woman (I suspect) whose name never got recorded the first time it was uttered “Only buy something that you’d be perfectly happy to hold if the market shut down for 10 years.” – Warren Buffett Imagine for a moment: The public secondary markets didn’t exist Investment pooling vehicles were all private, and no one published NAV estimates Stocks and bonds existed, but they were only formally offered through the companies themselves, and all private secondary trading was subject to a right of first refusal on the part of the issuing corporation. This includes short-term debts like commercial paper. Banks and life insurance companies still offer products to retail savers/investors, but nonforfeiture laws didn’t exist, and CD penalty clauses were very ugly. In other words, because of no public secondary markets, the price of liquidity was very high, with a strong incentive to hold financial instruments to their maturity date. Accounting rules are only partially standardized. Deposit insurance still exists. So does limited liability. In this thankfully fictitious world, what would investing be like? The main factor would be that liquidity would be dear. Because the “out” doors for liquidity are thin or closed for a long time, money would go into any investment only after great study. The 4 Cs of credit would be present with a vengeance – character, capacity, capital and conditions – and character would be chief among them as J. P. Morgan famously said. This would be true even if one were investing in the stock of a firm, rather than the debt. Investing in such a world, even with limited liability, is tantamount to an economic marriage back in a time where divorce was mostly for cause, and not easy to get. You’d have to be very certain of what you were doing. Perhaps you would diversify, but one would quickly realize how difficult it can be to keep up with a bunch of private firms – we take for granted how information flows today, but with private firms, you are subject to the board and management. What do they choose to share with outside passive minority investors? Excursus: It is said that it is easy to teach a child to say “please,” because it is the equivalent of “gimme.” It is harder to teach them “thank you,” until they realize that it means, “I’d like an option on the next deal.” Why would private firms choose to be open with outside private minority investors? They want a continuing flow of capital, and with no secondary markets, that can be difficult. Granted, there are always hucksters that say with P. T. Barnum, who is alleged to have said, ” There’s a sucker born every minute .” Those characters exist regardless of market structure, but in a healthy culture, they are a small minority in the markets. The same would apply to the debt markets. The fourth C, Conditions, would also impact matters. If you can’t get out easily/cheaply, then you will limit the term of the borrowing at which you are willing to lend, unless there are features allowing for participation in the upside, such as stock conversion rights. You might also find that insolvency becomes a very personal matter, as prior capital providers who know the business better than others, are invited to “prepackaged reorganizations” when the business is illiquid or insolvent. The bankruptcy code might still exist, but gaining enough data on a firm in trouble would probably prove difficult. The board and management, unless legally compelled, might not find it in their interests to be open. Control is a valuable option, one that is only surrendered when the situation is virtually hopeless. That said, a man very good at estimating character and business value could make some amazing profits, because “in the land of the blind, a one-eyed man is king.” And, the opposite would be true for many, as they get taken advantage of by less scrupulous management teams. Back to the Present “…[R]isk control is best done on the front end. On the back end, solutions are expensive, if they are available at all.” – Me, in this article , and a bunch of others. The purpose of what I just wrote is to get you to think about an illiquid world as a limiting concept. All of the problems of our world are there, usually in a form that is less severe than we experience because of the benefit of liquid secondary markets and vehicles for diversification. If valuable for no other reason, market panics make liquidity disappear, and it is useful to think about what you will do in an absence of liquidity before the time of trouble happens. The same is true of corporations needing liquidity. Buffett said something to the effect of, “Get financing before you need it; it may not be available later.” It’s also useful to consider more carefully the financial commitments that you make, so that you don’t make so many blunders. (True for me, too.) The ability to trade out of investments is useful but limited, because we don’t always recognize when we are wrong, and mechanical trading rules can lead us to the “death by one thousand cuts.” Beyond that, realize that character does matter. A lot. The government tries as hard as it can, but it is far better at punishing fraud after the fact than it is catching fraud before the fact. It will always be that way because the law is tilted in favor of the one in control; it has to be, or property rights are meaningless. But consider those that try to warn about financial disasters – they do not get listened to until it is too late. Madoff, Enron, housing bubble, various short sellers alleging improprieties, etc., etc. Very few listen to them, because seeming success talks far louder than an outsider. My counsel is the same as always, just look at the risk control quote above. But to make it stark, ask yourself this, a la Buffett, “Would you still buy this if you couldn’t sell it for ten years?” Then measure twice, thrice, ten times if needed, and cut once. Disclosure: None