26

As mentioned elsewhere on this site, Lo, Mamaysky, and Wang (2000) do exactly what you're talking about, namely algorithmic detection of head and shoulders patterns. Their definition: Head-and-shoulders (HS) and inverted head-and-shoulders (IHS) patterns are characterized by a sequence of five consecutive local extrema $E_1,...,E_5$ such that $$ HS \...


17

I would recommend that you read "Evidence-Based Technical Analysis" by David Aronson. Firstly, I am mentioning it because it is a highly worthwhile book. Secondly, on pp151--161 he attempts to "objectify subjective TA", using the head-and-shoulders pattern as an example.


14

Dynamic Time Warping, recursive, time-delayed feedforward neural networks, wavelets, empirical mode decomposition, ..., there's plenty of it. BUT If you want my advice, don't go this way, I wasted too much time doing things like that. Neither big nor small players (profitably and consistently) trade this way and for a good reason. Technical analysis is a ...


9

Yes, there are. For pure technical indicator libraries I would first check out: http://www.ta-lib.org/ Its open source and they provide APIs for both C# and Java among others. Let me know if you look for commercial ones but this one is definitely the most comprehensive in terms of open source code.


6

Remember that there is almost no point in predicting market movements if you cannot use it to trade and generate P&L. Thus, backtesting a stat arb strategy based on the indicator is best option. Don't let yourself fooled by correlation or even directional forecast percentage accuracy as a few wrong predictions can blow your capital. You will need a ...


6

J. Welles Wilder Jr created the indicator called the Relative Strength Indicator in 1967. The indicator he originally created uses all data points in the sample series, not just the last 14 data points (or whatever period of RSI you are using). Any data series that has less (or more) data than your current set will therefore show a different set of data. ...


5

One idea is Dynamic time warping (DTW). There is an R package for that: dtw Here is the vignette:Computing and Visualizing Dynamic Time Warping Alignments in R: The dtw Packageby Toni Giorgino And here is an example from Systematic Investor with full code: Time Series Matching with Dynamic Time Warping


5

This is one index I find to quite credible (Kansas City Fed Financial Stress Indicator): http://www.kansascityfed.org/research/indicatorsdata/kcfsi/


5

There is so much finance literature on this topic, I don't even know where to begin. Specifically on momentum, some of the earlier foundational papers are Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency Momentum Strategies Price Momentum and Trading Volume International Momentum Strategies Momentum has an entire page ...


5

The following paper gives you a range of different indicators and methods and, even better, unifies the whole concept: Which Trend Is Your Friend? by Levine, A., Pedersen, L. Abstract Managed-futures funds (sometimes called CTAs) trade predominantly on trends. There are several ways of identifying trends, either using heuristics or statistical ...


4

You might want to check out the book Evidence Based Technical Analysis by David Aronson. In it he applies statistical techniques to determine whether certain technical analysis indicators and ensembles have any predictive power. It's an interesting read and should equip you with some ideas on how you might perform a similar analysis.


4

There is, unfortunately, no broad agreement on this point. In fact, put-call ratios may be constructed from volume as well as open interest, and they can even be constructed from certain subsets of the options chain (e.g., only certain strikes or tenors). I have usually used your option #2, because option #1 has a tendency to be extremely high or even ...


4

I am not aware of a research specifically on integrating Macro view, but I'll give a shot at your question, hopefully it helps. I believe the answers depends on the initial trading strategies and on the macroeconomic indicators. From the way you formulate your question, I imagine that your trading strategy in based on quantitative asset allocation (mean-...


4

I think, the following list answers your question. Even though the below list is exhaustive, there might be some recent changes. Try looking for additional sources, you might find some more useful information. ADX Average Directional Movement Index ADXR Average Directional Movement Index Rating APO Absolute Price Oscillator AROON Aroon ...


3

I don't understand how technical indicators are at all relevant to the question. State probabilities can be generated directly from the returns if the model is known. There is no need to guess at heuristic trading rules based on technical indicators. Let $r_t$ be the return at time $t$. Your model is $E\{r_t | s_t=i\} \sim N(\mu_i,\sigma^2_i), i=0,1$ $P\{...


3

It seems that this is the key difference between OBV and TSV: "Time segmented volume is the way to get consistent volume data and eliminate all the volume distortions that we discussed above. Here's the key to why time segmented volume works: Let's start with volume on a 5 minute chart and for this example, look at the 10:15 bar. Now take the average of ...


3

There is considerable literature on the role of sentiment in predicting stock market returns. Sentiment is often used as the proxy variable to explain Risk Aversion. I would check out the following for details: Neal & Wheatley - Do measures of investor sentiment predict stock market returns Stambaugh - The Short of it: Investor sentiment and stock ...


3

Post-crisis there has been some research that uses return series for financial institutions to predict downturns. I think the major ones are CoVaR (Adrian and Brunnermeier) and CATFIN (Allen, Bali, and Tang). These lit reviews in these papers should provide a lot of background.


3

The most likely reason I can think of is the ease of computation. Gerald Appel developed the MACD in the late 1970's, when computing resources were very limited. When doing calculations by hand, on paper, it's much easier to take the difference of two simple (or exponential) moving averages than the log of their quotients.


3

I was searching for answers to the same question and came across your question. After some thought and research, here is the plan I have developed. I will be working in Python. Calculate relative maxima and minima with SciPy. Calculate RSI at those points using lib-ta. For each pair of lows and highs, compare the change in price with the difference in RSI. ...


3

Have you tried TA-lib? It supports RSI.


2

Renowned CXO Advisory Group have created a research compendium exclusively on momentum investing. This is the most exhaustive treatment of the topic I have ever seen: The Momentum Investing Research Compendium With $25 the price is reasonable.


2

Cliff Asness's PhD thesis was based on Momentum and Value. AQR has a lot of interesting research. http://www.aqrindex.com/AQR_Momentum_Indices/Momentum_Research/Content/default.fs http://aqr.com/Research/ByTopic.aspx Jegadeesh and Titman (Returns to Buying Winners...- first paper linked in the above answer ) seems to be the standard reference.


2

Here is another paper I found recently on using sentiment to predict equity markets: Risk Sentiment Index (RSI) and Market Anomalies


2

CBOE defines Put Call ratio as PCR = OIputs / OIcalls and I have always seen it defined this way. You should express it in a decimal way, a fraction doesn't really make sense here if you have 9999 in OIcall and 9998 in OIput for instance.


2

You might have a look into the CRAN's "Empirical Finance" task view. It lists a whole bunch of R packages for time-series analysis and construction of automatic trading rules. Link: http://cran.r-project.org/web/views/Finance.html


2

Regarding trading, it depends upon one's style and temperament. Don't rely solely on Aronson's book and his views and a phrase quoted by Andrew Lo in his study. The formula posted by Tal Fishman of Head and Shoulders as quoted by Lo, Mamaysky and Wang (2000) is not exhaustive. There is a lot of scope for further improvement. However, there are many studies ...


2

I answered @Anilca's question in SO (and the answer was accepted) I summarize my answer with the working solution: public class Aroon : IndicatorCalculatorBase { public override List<OhlcSample> OhlcList { get; set; } private readonly int _period; public int Period { get { return _period; } } public Aroon(int period)...


2

Yes, the function does not consider cases when the price is flat. The solution is very simple. Look at the OBV2 function below. The series from OBV and OBV2 are highly correlated, but the strict definition would be higher (smaller) depending on the market evolution. In the QQQ case that difference is about 50% 1. You could find the maintainer here: http://...


2

How should an n-day low be defined? Let's start with the simplest case: a 1 day low. We say that today is a 1 day low if the close of today is lower than the close of yesterday: $c_t<c_{t-1}$. This is the same as a Down Day. Generalizing, today is a 2-day low if $c_t<c_{t-1} \wedge c_t<c_{t-2} $. In words: today's close is below both yesterday's ...


Only top voted, non community-wiki answers of a minimum length are eligible