JimmyJam mentioned:
1. http://www.tradingpro.com/
they actually forecast S&P500, intraday predictions, as they claim
at the beginning of the day they forecast when to enter and exit the market for that day
Technical analysis with artificial intelligence
- Thread starter marklucas
- Start date
JimmyJam mentioned:
1. http://www.tradingpro.com/
they actually forecast S&P500, intraday predictions, as they claim
at the beginning of the day they forecast when to enter and exit the market for that day
http://www.askchart.com/
quoting from their website:
AskChart PowerTrade
$34.95/Month, including all exchange fees, 2-week no-risk free trial available
# Limited time offer: get AskChart Streamer FREE when you subscribe AskChart PowerTrade. AskChart PowerTrade offers one of the most sophisticated online end-of-day trading systems and strategies. Trading System Selector lets you find the most suitable trading strategy to trade a stock
# System Screener screens out the most-profitable stocks for each trading strategies
# Power Charts plots all buy and sell signals on a bullish-bearish-neutral zone charts
# PowerTrade recommended lists gives daily issues screened by AskChart Servers that can have potential higher profitability
# Plus these bonus, One the fastest realtime streaming quote applets
# Realtime web charts with full technical analysis
# Realtime market stats including most-actice issues, gainers/losers, 52-week highs/lows
# Over 70 major market indices
quoting from their website:
AskChart PowerTrade
$34.95/Month, including all exchange fees, 2-week no-risk free trial available
# Limited time offer: get AskChart Streamer FREE when you subscribe AskChart PowerTrade. AskChart PowerTrade offers one of the most sophisticated online end-of-day trading systems and strategies. Trading System Selector lets you find the most suitable trading strategy to trade a stock
# System Screener screens out the most-profitable stocks for each trading strategies
# Power Charts plots all buy and sell signals on a bullish-bearish-neutral zone charts
# PowerTrade recommended lists gives daily issues screened by AskChart Servers that can have potential higher profitability
# Plus these bonus, One the fastest realtime streaming quote applets
# Realtime web charts with full technical analysis
# Realtime market stats including most-actice issues, gainers/losers, 52-week highs/lows
# Over 70 major market indices
Stock Index Forecasting using Recurrent Neural Networks
S.-I. Wu and H. Zheng (USA)
Keywords:
Recurrent Neural Network, Financial Forecasting and Prediction, ARIMA, Time Series, Stock Market
Abstract:
We have developed two different architectures of recurrent neural networks (RNN) to forecast the daily closing prices of stock indexes (S&P500, Dow Jones, and NASDAQ) five days ahead. Experiments showed that the price is predictable and much better than the random guess. According to a simple short-term investment strategy, a good annual profit rate can be obtained. Different activation functions were tested in order to dynamically choose the best neural network topology. We explored more than 600 network structures for each neural network. The same data sets were analyzed by the ARIMA model using commercial statistics package MINITAB. The RNNs outperform a better result than the ARIMA model in terms of profit rates. The autoregressive parameter helped us determine the recurrent neural network structure
--
http://www.actapress.com/PaperInfo.aspx?PaperID=15048
S.-I. Wu and H. Zheng (USA)
Keywords:
Recurrent Neural Network, Financial Forecasting and Prediction, ARIMA, Time Series, Stock Market
Abstract:
We have developed two different architectures of recurrent neural networks (RNN) to forecast the daily closing prices of stock indexes (S&P500, Dow Jones, and NASDAQ) five days ahead. Experiments showed that the price is predictable and much better than the random guess. According to a simple short-term investment strategy, a good annual profit rate can be obtained. Different activation functions were tested in order to dynamically choose the best neural network topology. We explored more than 600 network structures for each neural network. The same data sets were analyzed by the ARIMA model using commercial statistics package MINITAB. The RNNs outperform a better result than the ARIMA model in terms of profit rates. The autoregressive parameter helped us determine the recurrent neural network structure
--
http://www.actapress.com/PaperInfo.aspx?PaperID=15048
SmartQuant Ltd
info@smartquant.com
Download QuantDeveloper Demo (20Mb).
Neural networks
Portfolio selection
General optimization
Portfolio optimization
Heuristic optimization
CAPM (Capital Asset Pricing Model)
Neural optimization
VaR (Value at Risk)
Genetic algorithms
Prospect Theory
Simulated annealing
Technical analysis
Taboo search
Data patterns
Game theory
Bond pricing
Multi-agent simulations
Option pricing
Monte Carlo simulations
Volatility estimations
Time series analysis
SWAP pricing
Fuzzy logic
Arbitrage trading
Fractals and chaos
Term structure
Neural networks
[1] Feedforward and Recurrent Neural Networks and Genetic Programs for Stock Market and Time Series Forecasting, P.C.McCluskey, 1993
[2] Clustering of the Self-Organizing Map , Juha Vesanto , 2000
[3] The Learning Vector Quantization Program Package, T.Kohonen, 1996
[4] A Neural Network Model for Gold Market, P.J.McCann, B.L.Kalman,1993
[5] Prediction Risk and Architecture Selection for Neural Networks
.....
--
http://www.smartquant.com/references.php
info@smartquant.com
Download QuantDeveloper Demo (20Mb).
Neural networks
Portfolio selection
General optimization
Portfolio optimization
Heuristic optimization
CAPM (Capital Asset Pricing Model)
Neural optimization
VaR (Value at Risk)
Genetic algorithms
Prospect Theory
Simulated annealing
Technical analysis
Taboo search
Data patterns
Game theory
Bond pricing
Multi-agent simulations
Option pricing
Monte Carlo simulations
Volatility estimations
Time series analysis
SWAP pricing
Fuzzy logic
Arbitrage trading
Fractals and chaos
Term structure
Neural networks
[1] Feedforward and Recurrent Neural Networks and Genetic Programs for Stock Market and Time Series Forecasting, P.C.McCluskey, 1993
[2] Clustering of the Self-Organizing Map , Juha Vesanto , 2000
[3] The Learning Vector Quantization Program Package, T.Kohonen, 1996
[4] A Neural Network Model for Gold Market, P.J.McCann, B.L.Kalman,1993
[5] Prediction Risk and Architecture Selection for Neural Networks
.....
--
http://www.smartquant.com/references.php
It is much the same old story as the Great Californian goldrush. The people that made the money were the sellers of booze, picks and shovels etc. not the 49'ers generally. Their success rate was probably about the same as trading, with a few notable exceptions , which publicised the goldfields nicely. Over 90% failure rate in both areas of activity and populated by very similiar people.
Sorry to poor cold water on what is a fascinating subject but........
Do you reaaly believe the scamsters and snake-oil vendors can predict the future ? No way. They just see a load of suckers ( like me too ) they can con with ease.
Sorry to poor cold water on what is a fascinating subject but........
Do you reaaly believe the scamsters and snake-oil vendors can predict the future ? No way. They just see a load of suckers ( like me too ) they can con with ease.
One more insight on using AI/NN:
http://www.investopedia.com/articles/trading/06/neuralnetworks.asp
http://www.investopedia.com/articles/trading/06/neuralnetworks.asp