Welcome, Guest. Please Login
Algorithmic Trading Forum
 
  HomeHelpSearchLogin  
 
Poll Poll
Question: What do you think about this section?

I like it. Bring more papers  
  9 (90%)
It could be better. Let me help  
  1 (10%)
Stop it right now  
  0 (0%)




Total votes: 10
« Created by: Co0olCat on: 07/11/08 at 08:32:25 »

Pages: 1
Send Topic Print
White papers on Complex Event Processing (Read 28442 times)
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
White papers on Complex Event Processing
07/11/08 at 08:30:51
 
This section lists white papers on Complex Event Processing (CEP).
CEP constitutes important part of Algorithmic trading engines.
Since we respect copyright the section contains only links to external sources and short abstracts.

For consistency use following formatting:

Surname#1, N#1. and N#2., Surname#2 (or Surname#1, N#1 et al), date of publication, source

Paper Title
http://link

Abstract

Short abstract.
Back to top
 
 

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
Re: White papers on Complex Event Processing
Reply #1 - 07/11/08 at 08:44:09
 
Tivegna, M., April 2003, presented at The Tenth International Conference on :Forecasting Financial Markes: Advances for Exchange Rates, Interest Rates and Asset Management", Paris June 4-6 2003

Day Trading the Euro-Dollar with a News-Based Model of Exchange Rates. Descriptive Results
http://www.cide.info/conf_old/papers/1164.pdf

Abstract

The paper presents some first results on how to use a news-based model of the EUR-USD and USD-YEN exchange rates with GARCH error terms to generate day-values were used to draw three trading bands, Base, EUR-Strong, EUR-Weak to devise strategies for opening up trading positions according to where - inside or outside of them - the exchange rate falls in the morning in Cetral European Time. Trades were closed according to two procedures described in the paper. These trading rules generate a high number of profitable signals and the profit rates cluster between 10 and 20 percent, reaching 25%. Some profitable trading rules described in the paper may operate as unsupervised automatic day-trading machines. Positive Sharpe Ratios lay between 1.5 and 5.6. These results were obtained over a sample of 360 trading days in 2001 and 2002.
Back to top
 
 

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
Re: White papers on Complex Event Processing
Reply #2 - 07/11/08 at 10:35:11
 
Fornari, F. and A. Mele, 2001, Applied Financial Economics 11

Volatility Smiles and the Information Content of News
http://fmg.lse.ac.uk/~antonio/files/afe01.pdf

Abstract

The paper investigates whether the impact of selected news – scheduled and unscheduled – affects only the current conditional variance of financial prices or, by bringing new information to the market, induces also a revision of the implied variance, i.e. the variance expected to prevail over the life to maturity of an option. The latter phenomenon would signal that news is able to change permanently the consensus on the future economic environment. In addition to recent similar analyses which employ the at-the-money implied volatility to this aim, tests are also performed on the implied out-of-money and in-the-money volatilities. These are in fact extremely sensitive to lack of information about the future evolution of the price of the underlying asset: hence, their prices - as well as their implied volatilities - must change significantly after the occurrence of important events.
Back to top
 
 

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
Re: White papers on Complex Event Processing
Reply #3 - 07/11/08 at 10:38:55
 
Abberger, K. and K. Wohlrabe, March 1, 2007

The High-Frequency Response of Ifo Business Climate Announcements
http://www.lrz-muenchen.de/~u5001ah/webserver/webdata/paper/Wohlrabe.pdf

Abstract

Using a ten year data set consisting of real-time Euro/Dollar exchange rate quotations we investigate in an event study the high-frequency response of Ifo Business Climate announcements. In particular, using two expectations series of the Ifo Business Climate, we find that announcement surprises generates a positive level effect for several minutes just after the release. The impact is symmetric and does not depend on the size of the surprise. The bid-ask spread widens after positive surprises. Furthermore the release of the Ifo Business Climate itself has a significant level and volatility effect on the exchange rate market. The price volatility is much higher on announcement days than on nonannouncement days.
Back to top
 
 

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
Re: White papers on Complex Event Processing
Reply #4 - 07/11/08 at 10:46:39
 
Tivegna, M, March 2008, presented at International Conference MAF 2008: Mathematical and Statistical Methods for Actuarial Sciences and Finance

Day-Trading the Main Currency Pairs with a News-Based Model of Exchange Rates
http://maf2008.unive.it/viewpaper.php?id=65

Abstract

The paper presents trading results obtained by using a news-based model of the (EUR-USD), (GBP-USD) and (USD-JPY) exchange rates with GARCH error terms to generate day-trading signals on the (EUR-USD) and (GBP-USD). A novel feature of this paper consists of the thrice-daily frequency of the model. Baseline and conditional model forecasts were used to generate trading signals in order to devise strategies for day-trading. A group of these strategies can be managed by an unsupervised trading machine. One rule replicates a possible behaviour of a news trader. Given the thrice-daily frequency of the model, trading signals are produced for two (at the moment) trading areas: European Time Zone (ETZ) and American Time Zone (ATZ). Several typologies of trading are described; most of them open up trades at the beginning of ETZ. Closing protocols are different across the various strategies. The model is estimated between 1999 and 2004 and trades in 2005. These rules generate a high number of profitable signals and the profit rates reach, under various measures, 60%, yearly basis, floating, on a median level, around lower levels.
Back to top
 
 

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
Re: White papers on Complex Event Processing
Reply #5 - 07/11/08 at 10:52:18
 
Bertoluzzo, F. and M. Corazza, March 2008, presented at International Conference MAF 2008: Mathematical and Statistical Methods for Actuarial Sciences and Finance

Recurrent Reinforcement Learning-Based Trading Systems
http://maf2008.unive.it/viewpaper.php?id=114

Abstract

In this paper we propose a financial trading system whose strategy is developed by means of an artificial neural network approach based on a recurrent reinforcement learning algorithm. In general terms, this kind of approach consists in specifying a trading policy based on some predetermined investor's measure of profitability, and in setting the financial trading system while using it. In particular, with respect to the prominent literature, in this contribution: First, we take into account as measure of profitability the reciprocal of the returns weighted direction symmetry index instead of the wide-spread Sharpe ratio; second, we obtain the differential version of this measure of profitability and obtain all the related learning relationships; third, we propose a procedure for the management of drawdown-like phenomena; finally, we apply our financial trading approach to some of the major world financial market indices.
Back to top
 
 

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
Re: White papers on Complex Event Processing
Reply #6 - 07/11/08 at 10:58:06
 
Grilli, L. et al, March 2008, presented at International Conference MAF 2008: Mathematical and Statistical Methods for Actuarial Sciences and Finance

Financial Time Series and Neural Networks in a Minority game Context
http://maf2008.unive.it/viewpaper.php?id=83

Abstract

In this paper we consider financial time series from U.S. Fixed Income Market, S&P500, DJ Eurostoxx 50, Dow Jones, Mibtel and Nikkei 225. It is well known that financial time series reveal some anomalies as regards the Efficient Market Hypotesis and some scaling behavior, such as fat tails and clustered volatility, is evident. This suggests to consider financial time series as "pseudo"-random. For this kind of time series the prediction power of neural networks has been shown to be quite appreciable [10]. At first, we consider the financial time series from the Minority Game point of view and then we apply a neural network with learning algorithm in order to analyze its prediction power. We prove that Fixed Income Market shows many differences from other markets in terms of predictability as a measure of market efficiency.
Back to top
 
 

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
Re: White papers on Complex Event Processing
Reply #7 - 07/11/08 at 14:37:16
 
Ventana Research, June 2008
The Emerging Role of News Feeds for Algorithmic Trading & Advanced Decision Support


Abstract

Ventana Research recently conducted a study into the opinions and attitudes of trading and investing professionals regarding automating news analysis. There were 113 qualified participants in the research. The group represented a diverse set of respondents: 38 percent work in buy-side firms (investment management, hedge fund or private equity/venture capital), 37 percent are on the sell side (investment bank or broker/dealer), and the remaining 25 percent work in other types of organizations.

In terms of scope, about one-third (36%) of the participants’ organizations have a single trading desk, another 52 percent have multiple desks, and the remaining 12 percent have some other configuration. In terms of trading style, 18 percent described their organization as ultra-high frequency, 24 percent high frequency, 41 percent medium frequency and 17 percent low frequency. More than half (57%) describe their investment and trading style as fundamental, another one-third (35%) as quantitative and 8 percent as statistical arbitrage.

A majority (58%) of the participants work in firms with fewer than 100 employees, 22% are in organizations with between 100 and 999 employees, and the remaining one-fifth are in companies with 1,000 or more employees.
Back to top
 
« Last Edit: 09/05/08 at 12:37:59 by Co0olCat »  

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Co0olCat
Forum Moderator
*****
Offline



Posts: 128

Gender: male
Re: White papers on Complex Event Processing
Reply #8 - 07/29/08 at 10:12:36
 
Peramunetilleke, D. and R. K. Wong, 2001, the  Thirteenth  Australasian  Database Conference (ADC2002), Melbourne, Australia.  Conferences in Research  and  Practice  in  Information  Technology,  Vol.  5. Xiaofang Zhou, Ed.

Currency Exchange Rate Forecasting from News Headlines
http://crpit.com/confpapers/CRPITV5Peramunetilleke.pdf

Abstract

We  investigate how money market news headlines can be used to  forecast  intraday  currency  exchange  rate  movements.  The innovation  of  the  approach  is  that,  unlike  analysis  based  on quantifiable  information,  the  forecasts  are  produced  from  text describing the current status of world financial markets, as well as political and general economic news.  In contrast  to numeric time series data textual data contains not only the effect (e.g., the dollar  rises  against  the  Deutschmark)  but  also  the  possible causes  of  the  event  (e.g.,  because  of  a  weak  German  bond market). Hence  improved  predictions  are  expected  from  this richer input. The output is a categorical forecast about currency exchange  rates: the  dollar  moves  up,  remains  steady  or  goes down within the next one, two or three hours respectively. On a publicly  available  commercial  data  set  the  system  produces results that are significantly better  than  random prediction. The contribution  of  this  research  is  the  smart  modeling  of  the prediction  problem  enabling  the  use  of  content  rich  text  for forecasting purposes.
Back to top
 
 

"Yesterday is history. Tomorrow is a mystery. But today is a gift, and that is why it's called the present."
WWW timuryusupov   IP Logged
Pages: 1
Send Topic Print