Volatility is an interesting subject. For some it is risk and for others it is opportunity. In a way I think it is both. For a trader, price volatility creates opportunity whereas portfolio volatility creates risk.
Typically in statistical sampling, extreme outliers are treated as spurious samples and left out. That way the sampled data can fit nicely with more elegant statistical distributions and can be explained well by models. On other hand the premise of technical analysis is "markets are inefficient and one can profit from these inefficiencies".
TA typically assumes the market price moves are a proxy for the information content and price inefficiencies. So technical trading rules typically have a price & time scale parameter like number of days for purpose of smoothing data, to reflect some cycle length and to identify market inefficiency to profit. So far good.
When it comes to markets, the days with large price moves are the ones that reflect most the inefficiencies and also trigger the most emotions. No
w a rarely asked but important question is would your technical indicators yield better performance when you consider only information rich large price move days versus considering all days?
I recently came across a paper that targets this question. What the author does is uses volatility as a filter to screen out noise (i.e., flat days) and include only days that are rich in information. Once these flat days are filtered out, then the author applies the same trading rules on non-filtered days and does before-n-after trading rules performance comparison.
So what are filtered days?
The paper first defines a threshold and then uses this threshold to filter out some of the days in the sample. The threshold is for example like a 25% of sample daily return's standard deviation of the full set. Now using this threshold, we filter out nearly all flat days (i.e., days with gain or loss less than threshold) from the full sample. The days of interest to us here is the retained set i.e., non-filtered days in the sample.
Trading Systems & Data
To validate whether this filtering helps, the paper picks three trading rules/systems and compares the performance of these three systems on full sample data vs performance on retained data (i.e., data where flat days were filtered out). The data is SPX daily index for last 23 years i.e., 1990-2012. I think this is long enough data.
Short Term System: 2 day run mean reversion
Rules:
- Long 100% in SPX at the market close of a trading day when index has been down 2 days in a row.
- Short 100% in SPX at the market close of a trading day when index has been up 2 day in a row.
- Continue with current position (long or short) till a switching conditions has not been met.
Filtering schemes:
- Scheme 1 - Apply a fixed filter i.e., ignore days that have less than 25% of SPX daily return standard deviation. The standard deviation was calculated for the entire period.
- Scheme 2 - Filter all days that have returns less than 20% of SPX daily return standard deviation. This standard deviation was calculated on last 60 days of rolling window.
- Scheme 3 - Filter all days where threshold is 22% of current SPX index option implied volatility.
The concept applied for short term system is basically ignore nearly flat days and focus on market moving days to improve your short term trading rules performance. This is similar to volatility filtering systems that one hears about in TA.
I am not sure filtering schemes 1 & 3 would be robust. I generally prefer to stay away from thresholds that are absolutes. Also these two filtering schemes has a look ahead bias.
Intermediate Term System: Dual Moving Average Cross (DMAC)
Rules:
- Go Long when short term moving average crosses above long term moving average
- Go Short when short term moving average crosses below long term moving average.
Filtering scheme:
- Filter all days whose daily returns are less than 0.25% daily returns of SPX when computing SMA and LMA.
The concept that gets applied indirectly here for intermediate term system (i.e., MA system) is to increase the MA length when there are many flat days. So in other words the simple MA becomes an adaptive MA.
I am not fully convinced yet that filtering out nearly flat days is the way to apply this concept. Part of the reason is most bars effect (unless they were in key locations) will fizzle out in few days. Whereas the system we are talking here is intermediate term system. Another reason is the equity curve seems bad last 3-4 years. Don't know if it is due to change of market character since financial crisis and popularity of risk aversion.
Long Term System: Price Channel Trading
Rules:
- Switch to long when close is greater then m day price channel high.
- Switch to short when close is below the m day price channel low.
Filtering schemes:
- Filter all days in channel calculations whose daily returns are less that 0.25% of daily SPX return.
Here I am not sure why the filtering scheme is improving the performance. Basically what we are saying is when we have too many flat days, then increase the channel look back period. I would think the other way (i.e., decreasing the the channel look back period when too many flat days) would be more profitable. The rationale - volatility contraction.
Concluding thoughts:
I think on the whole the core concepts in this paper are good. But on other hand, I don't feel comfortable with absolute thresholds and especially if they were calculated by looking ahead.
My main take away from the paper is utilizing of this filtering concept but probably in a different way for a short term system. For intermediate and long term systems, probably I will skip this concept for now.
For any one interested in reading full paper, following are the details -
Source - "Filtered Market Statistics and Technical Trading Rules", George Yang, May 2013.
Wish you all good health and good trading!!!
Few weeks back I came across an interesting paper on insider trading. This paper is about detecting patterns in trades made by insiders to identify suspicious trades for investigators and prosecutors. Another audience for the paper naturally is us i.e., traders/investors.
For example, can you tell from a set of insider trades which of the trades are made by an informed insider to take advantage of an information that is not yet public? Can you figure which of the trades of this informed insider are to capitalize on private information that is short lived in nature? How about figuring which of the insider trades are to capitalize on private information that is long term in nature i.e., it will be revealed to public few months months down the line?
Before diving into the journal paper, couple of points -
- There are many ways insiders can take advantage of private information like through options/insider phone tree/sharing with others knowingly/unknowingly etc. This paper primarily focuses on the publicly available trading records of the insider.
- To me no one single concept makes up a system. Also when I investigate journals, I don't look for a system. What I look for is ideas that I can later on investigate myself and may be mix & match with other ideas. A select few of these ideas become additional qualifiers (at process level) to my existing methods and contribute to position timing/sizing decisions.
So what are some insider trading patterns?
Often when articles on the net talk about analyzing insider trading, the typical suggestions are like those below
- Insider purchases are good indicator of future prospects of the stock. That is the main reason for an insider to buy.
- No reliable information from insider sales about future prospects of the stock. An insider might sell stock for any number of reasons like diversification or a need to raise money for some thing etc.
- Another type of suggestion - look at how insiders fared with their past purchases. If they did well then they might do well again.
- Similarly another type of suggestion - See how many insiders are purchasing? Also see what is the trend of insider purchases and sales. The idea here being the more insiders purchase the better it is.
- Another type of suggestion - See the dollar amounts of insider purchases or see the change in total holdings. The idea here being the bigger the amount the higher the confidence of insiders in future prospects of the stock.
Now while the above suggestions sound logical and may have an edge (which I don't know), one problem is they treat all insider trades as equal. Ok, some go little farther by differentiating the trades from executives and others. But one thing missing is they don't take into consideration the trading patterns/behaviors of the insiders.
Pattern-1: Sequenced Trading Pattern
Not all private information is equal. Some private information has advantage that is longer lived. While other types of information has advantage that is only short lived.
Consider a hypothetical company where the CEO/another C staff member of that company was involved in private negotiation with a key supplier or customer. Assume the outcome of these negotiations have long-term earnings implications. Now say the negotiations are not going well.
Obviously the insider will know that. The thing is this information has no near term earnings implication. Also this information will not be revealed to the public for another 6 months or so. So how would the executive take advantage of this insider information?
Given the executive is not in a hurry, the typical pattern is for the executive to spread their trades over several months. Also given the luxury of time, the insider likely might execute trades (reported to the SEC) on Fridays. Why Friday? I will cover this in a future post. Gist is, of all days of the week, Friday's have least investor attention. So why not take advantage of that as the insider have flexibility and less immediacy.
Just FYI...it is ok if you feel the above info does not lend easily to quantify. For now go with concept level. Later in the post, I will write the objective rules to identify a sequenced trading pattern. If that is not sufficient and don't mind putting up with equations and extraneous stuff, then you can read the source paper itself.
Pattern-2: Isolated Trading Pattern
Say at a firm an executive have been receiving internal field reports of lower than expected sales reports. The executive knows that the firm is likely to miss its earnings in the near term.
Now this is a short lived information and the insider has to act quickly before the information is revealed to the public. The insider in this case is most likely to engage in isolated (often singular trades) concentrated in a particular month. The paper calls these trades isolated trading pattern.
The idea behind this pattern is when insiders have access to short lived information, they most likely make isolated and often singular trades or trades that fall within same month (or 30 days).
As I mentioned earlier, this paper is also for investigators/prosecutors. Now for them, they don't need to know an insider made the trade on private information before the information becomes public and market reflects that info in the stock price.
I mean say an insider made trades following this pattern. After that soon the stock tanks/zooms up when the information becomes public. For investigator, that is enough to determine the trade is likely based on private information. But as traders we need to know that trade is likely based on private information before the market reflects private information.
From what I understood, at least in the paper there is no way to detect trades of Isolated Trading Pattern before hand. Also this pattern is a sub pattern of "Sequenced Trading Pattern" and there is no way to distinguish between these two patterns till a month passes by after the trade. The results in paper are for that one month where we were supposed to be waiting to determine the trade belongs to an Isolated Trading Pattern.
On other hand, we can identify Sequenced Trading pattern objectively. Also over several thousand samples, the data in the paper indicates a good positive edge for this pattern over multiple months. So in rest of the post, I will focus only on Sequenced Trading pattern.
How to identify a Sequenced Trading Pattern?
The rules for identifying sequenced trading pattern are
- For each insider, aggregate all the trades on a calendar month basis.
- The trades of the insider should occur in consecutive calendar months. If there is a gap of more than one calendar month between trades in the sequence then it is not a Sequenced Trading Pattern.
- Finally the insider trades are not routine trades. A trade is considered as routine trade if the insider has traded in same calendar month in three consecutive years.
Observations:
When I understood the rules, I thought there won't be that many samples. It is surprising that there are so many samples available as the below figure indicates.
Portfolio Construction?
If insiders engage in sequence of trades solely for diversification and liquidity purposes, then any portfolio constructed over sequenced trading pattern should have typical returns. On other hand, if there is private information that is being taken advantage by executive insiders then there would be good returns following their end of sequences and portfolio based on this pattern should have abnormal returns.
Rules:
- At the beginning of each month, look for stocks that have "sequenced trading pattern". Note: The earliest date we can determine a sequenced trading pattern is one calendar month after the last trade of the sequence is complete.
- Add the stocks that meet the pattern criteria to the portfolio.
- Added stocks will be kept in the portfolio for the month.
- Re-balance the portfolio at the beginning of the next month based on new stocks that complete the insider sequence trading pattern.
Results & Observations?
Following image provides the results of the sequenced trading pattern portfolio along with my annotations. Please see the images for context to below paragraph.
While the concept and results are interesting, what piqued my interest also is that (a) while the sequence is underway, the stock goes against the direction of the insider trades and (b) there is no return significance while the sequence is underway. Now add to that a price action entry technique to control risk. May be it is my contrary antennae going up but it feels that is a worthwhile and possibly another profitable angle for any interested readers.
To all readers, thank you for visiting my blog. I hope the above post is interesting and informative to you. Most of this site visitors are by word of mouth reference. So if you found this and other posts on the blog interesting and useful then please suggest the site to couple of your friends/colleagues. I appreciate it.
Source Paper: Insider Trading Patterns.
Side note:
I have not verified myself whether the pattern has positive edge. I don't have access to historical insider trade data in a tabular/csv format. To get that data either one needs to subscribe to an expensive data feed (but I rarely trade stocks now) or write a robot to traverse and scrape SEC filings/pages to generate the data set automatically. I don't have time for the later option. Few weeks back I joined a very small but rapidly growing and cash flow positive firm. So now a days I don't get much time beyond firm work, trading and family. So I guess for now these action items are going into my trading BOT book. (BOT - Book of ToDo).
Wish you all good health and good trading!