The Importance of This Website

The Importance of This Website to Your Business

World Financial Markets Are Nonstationary. This can be viewed in terms of the evolution of the structure underpinning any particular market. Moreover, any parameterization in a market model will have a half-life. That is, the usefulness of the model's parameters will decay over time. Consequently, it is essential that a market model be constructed in such a way that its parameters can adapt as market forces change. A characteristic of this phenomenon is that a model's parameters migrate in parameter space as the model adapts to modest movement in the underlying market structure.

In the past, major nonstationary shifts have occurred every year or so in most major markets, and have, sometimes, been associated with recognizable events. An example of a recurring event in the Bond market would be a Fed policy change (or perception thereof) from increasing to decreasing (or decreasing to increasing) short term interest rates. In the currencies, both the announcement of the agreement to implement the Euro and its actual introduction caused structural shifts. Recently, Fed policy intended to improve the American trade imbalance, at the expense of the otherwise strong Dollar, caused precious metals market structure to shift, as gold began acting more like a currency than a commodity.

Your Models Might Stop Working Some Day. Sometimes, nonstationary market shifts are substantial, causing model parameters to leapfrog rather than migrate. Sometimes, in spite of one's best efforts, models stop working at all. This is especially true for trend following, momentum, and technical analysis based market models. That's OK. Adjustment to market models—even re-writing them—is part of the market quant's job description.

Nonstationary Effects Are Becoming More Frequent. Having said that, any market quant, who is actively modeling today's markets, can attest to the fact that the nonstationarities have been occurring with increasing frequency. This may be caused by globalization of markets; more efficient mechanisms for disintermediation of traders' funds between foreign and domestic equity, fixed income, commodity, forex, and mutual fund markets; or whatever.

Your Quants Need Training To Deal With This Problem. Perhaps your Quants already handle this new problem with ease, in which case you are probably prepared to survive these increasingly turbulent markets. Unfortunately, it is not just the nonstationarity events, but the decreasing intervals between them that cause havoc to the market modeler. The shorter the timeframes, the less market data one has with which one may train. Moreover, the less market data one has, the more difficult it is to establish statistical validity. There are techniques which can help to maintain statistical validity. Switching from traditional linear cross-validation to vertical or walk-forward cross-validation techniques may save your model. So, if (a) your models are not performing as they used to perform, (b) your quants are spending increasing amounts of valuable time attempting to keep them "tuned," (c) you wish to diversify your technology, or (d) your technology does not incorporate exogenous data, then consider protecting your investment in people and technology with some continuing education.

They Need A Sophisticated Quant Workstation. It is likely that you have a quant staff capable of doing their own programming. This is important. They are probably programming with "C," Visual Basic, Matlab, Mathematica, or Excel. They may already be using a quant workstation. Seminars taught by Applied Market Analytics, Inc. use a proprietary Quant Workstation and Quant Command Language ("QCL"). The QCL is unique, in that it offers a complete range of database access tools, user friendly commands, powerful mathematical transformations, statistical functions, and optimization facilities. Furthermore, it allows your quants to write and incorporate their own mathematical transformations to exploit your proprietary data and ideas, resulting in models that are uniquely yours.

Your Quants Need A Productivity Tool of Thought. Quant productivity is often diminished by the time lag between the origination of a modeling idea and the testing of that idea with actual market data. The QCL allows quants to test most ideas as they occur, using a set of over 1200 user commands.

Additionally, an extremely efficient high level language allows them to program new transformations with great ease, making their own commands. Programming new transformations and new commands "on-the-fly" does not require the compiling, linking, and reloading of data time series. One can originate new commands, incorporate them into the Command Language system, and begin using them without shutting down or restarting the modeling system.

Most programming languages require the programmer to deal with scalar data—one value at a time. This requires that the quant program with "loops" to handle time series data. The QCL's powerful model prototyping facilities avoid these time delays by processing time series as array objects. If, for example, the variables A, B, C, D, and E represent the time series for five stocks in a sector, and the quant desires the sector mean, then it is immediately available as time series M, after executing the following statement:

M <— MEAN A + B + C + D + E

Even the function "MEAN" had been programmed without loops, as Z <— +/ X ¸ r X

where Z is replaced by ( <— ) the sum of all X (+/ X) divided (¸) by the count of the elements in X (r X).

Your Portfolio Will Be Better Diversified With Exogenous Data Based Models. Exogenous data, in this discussion, is data which is neither derived from nor related to the price of the instrument being traded or market indices of its market. There are several general groups of exogenous data that can be used, including: volatility, sentiment, options, monetary, basis, and inter-market data. The purpose of using exogenous data is to exploit inefficiencies that are not within the view of the thousands of other market participants. These other market participants are mostly using price data within trend following, momentum, and technical analysis based trading systems.

Volatility data (e.g. OEX implied volatility, NASDAQ 100 volatility, and CBOE NASDAQ volatility indices) has been used successfully by many traders to generate trading indicators. Monetary data (e.g. Fed Funds, US Discount Rate, Yield curve) frequently serves also as intermarket data for building indicators for the equities markets. Sentiment data (e.g. various consumer sentiment indicators, block sales, retail sales, column inches of help wanted ads, etc.) also has a following of market traders.

Trade the Underlying Security With Indicators

Based on the Sentiment Information In Option Data

Whether you are trading commodities, energy, equities, market indices, ETFs, Forex, or fixed income securities, options data is the most useful class of sentiment data for modeling. Options data represents the sentiment of, arguably, the most knowledgeable market participants. (Options traders who are not exceptionally perceptive do not last very long in the option pits.) The traders of options are totally focused on the future direction of their respective markets. Options data represents a very wide range of sentiment about the market. On any market day, Microsoft common stock will have price data including Open, High, Low, Close, and Volume values. On that same day, there may be two thousand different active options contracts, several hundred of which may have trading volume. These active contracts will include several expirations (plus Leaps), valued at many different strike prices, traded on four exchanges. On October 7, 2003, the S&P 500 Index options included 59 strike prices with 8 expirations, for a total of 472 different instruments, all representing the collective sentiment of many traders. And, open interest existed for 420 calls and 428 puts among these option contracts.

The reasons for building indicators with option data for trading the underlying are:

1. Information contained in Options data reflects the forward looking sentiment of the smartest market players;

2. Option data includes both bullish and bearish sentiment information;

3. Related Volume and Open Interest data provide additional information indicating the strength of the sentiment information in the put and call premiums.

4. Most users of Option data are pricing put and call premiums, not building trading indicators for the underlying instrument;

5. An Options database is quite difficult to maintain, eliminating most would be competitors for exploiting the inefficiencies therein;

6. Inefficiencies in seldom used data tend to remain exploitable for longer periods, i.e. models work longer; and

Statistical validity is never a problem because of the quantity of information present every day.

Click HERE to see how the above can be developed into a Trading Strategy.

Exogenous Data Based Models – The good and bad characteristics of Exogenous Data. (Don’t miss the interesting visualization of some SPX Index Option data.)

Visualization of Exogenous Data – In case you missed it above.

Quantitative Analysis Platform – A user-friendly modeling platform for improving the productivity of quantitative analysts.

Overview – Advanced Automated trading Systems.

Consulting Services – Helping your quantitative analysts deliver a better product for your clients.

Trading Model Building Services – Continuous and Discrete Models, using Price or Exogenous Data.

Quantitative Analysis Training Seminars – Topics covered in typical training seminars.

Model Validation – A Catch-22 in the struggle between the Central Limit Theorem and the “Law” of Requisite Variety.

Non Trend-Following, Non Technical Analysis Methods – The difference that a non-price market view can make in your portfolio’s success.

Back to Home Page