PresentationPDF Available

Presentation ICIIS 2019 - A prediction model using the price cyclicality function optimized for algorithmic trading in financial markets

Authors:

Abstract

After the widespread release of electronic trading, automated trading systems have become a significant part of the business intelligence system of any modern financial investment company. An important part of the trades is made completely automatically today by computers using mathematical algorithms. The trading decisions are taken almost instantly by logical models and the orders are sent by low-latency automatic systems. This paper will present a real-time price prediction methodology designed especially for algorithmic trading. Based on the price cyclicality function, the methodology revealed will generate price cyclicality bands to predict the optimal levels for the entries and exits. In order to automate the trading decisions, the cyclicality bands will generate automated trading signals. We have found that the model can be used with good results to predict the changes in market behavior. Using these predictions, the model can automatically adapt the trading signals in real-time to maximize the trading results. The paper will reveal the methodology to optimize and implement this model in automated trading systems. After tests, it is proved that this methodology can be applied with good efficiency in different timeframes. Real trading results will be also displayed and analyzed in order to qualify the methodology and to compare it with other models. As a conclusion, it was found that the price prediction model using the price cyclicality function is a reliable trading methodology for algorithmic trading in the financial market.
INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATION SYSTEMS
ICIIS 2019, 8-9 APRIL 2019, ATHENS, GREECE
A PREDICTION MODEL USING THE PRICE
CYCLICALITY FUNCTION OPTIMIZED FOR
ALGORITHMIC TRADING IN FINANCIAL MARKET
Cristian Păuna
Economic Informatics Doctoral School
Bucharest University of Economic Studies
Email: cristian.pauna@ie.ase.ro
Phone: +407.4003.0000
This paper was co-financed by
the Bucharest University of
Economic Studies during the
Ph.D. program and Algorithm
Invest company (algoinvest.biz)
A PREDICTION MODEL USING THE PRICE CYCLICALITY FUNCTION
OPTIMIZED FOR ALGORITHMIC TRADING IN FINANCIAL MARKET
This paper presents:
Price Cyclicality Function (PCY)
Price Prediction Line (PPL)
Price Prediction Bands (PPB)
When to buy and when to sell
How to set the stop loss
When to close profitable trades
How to automate the model
In order to make profit
In any financial market
It was found that:
PCY is a reliable trend indicator
Parabolic Stop and Reverse (PSAR)
together with PPL build a reliable
trading model incorporated in PPB
There are two major profit levels
PPB can be used to trade UP trends
PPB can be used to define oversold
price levels for low risk trades
The presented trading model can
be fully automated
We have obtained good results
PRICE CYCLICALITY FUNCTION
PRICE PREDICTION LINE
Daily price evolution for
Frankfurt Stock Exchange
Deutscher Aktienindex
between Jun and Aug 2018
PRICE PREDICTION BANDS
FOR DOWNTREND
PRICE PREDICTION BANDS
FOR UPTREND
TRADING SIGNALS
When uptrend begins
For expansion periods of an uptrend
For the rest cases of an uptrend
For oversold prices in an unexpanded period
TRADING PROCESS AUTOMATION
CUMULATIVE RESULTS
COMPARATIVE RESULTS
CONCLUSIONS
PCY + PPL + PSAR = PPB
PPB can be used to develop a reliable and complete trading algorithm
PPB will define the entry points, the stop-loss level and the take profit price values
PPB trading model can be fully automated in any algorithmic trading system
PPB model can generate four different automated trading signal types
PPB trading methodology was tested with good results for several markets
(DAX30, DJIA30, FTSE100, CAC40, SMI20, ASX200,
NIKKEI225, NASDAQ100, S&P500, RUSSELL2000)
The cumulative results are conclusive, it was obtained RRR level of 1:6.53
The comparative results are also suggestive, with RRR level of 1:8.22
PPB is a simple and complete automated trading methodology for any market
PPB has a small number of functional parameters that can be optimized for any market
PPB can be used as a data-mining filter in order to improve any other trading methodology
PPB can be adapted for automated investment systems using larger time frames
This paper was co-financed by
the Bucharest University of
Economic Studies during the
Ph.D. program and Algorithm
Invest company (algoinvest.biz)
ResearchGate has not been able to resolve any citations for this publication.
ResearchGate has not been able to resolve any references for this publication.