Skip to main content

Advertisement

Log in

Ultra-short-term trading system using a neural network-based ensemble of financial technical indicators

  • S.I. : Information, Intelligence, Systems and Applications
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

The proposed paper presents the analysis, design, implementation and evaluation of an ultra-short-term frequency trading system for the foreign exchange (FOREX) market, which features all stages of the trading process (Pretrade Analysis, Trend Forecasting, Transaction Execution) substantially exploiting artificial intelligence techniques. Our goal is to simulate the judgment and decision making of the human expert (technical analyst or broker) with a system that responds in a timely manner to changes in market conditions, thus allowing the optimization of ultra-short-term transactions. We designed and implemented a series of technical indicator simulators, which are fed to a novel artificial neural network architecture, to eventually generate the trend forecasting signal. We also designed and implemented a series of customizable ultra-short-term automated trading machines, which receive as inputs the generated forecasting signals and perform real-time virtual transactions. A comparative analysis of the results of both automated trading machines and each machine is carried out for a comprehensive variety of trend forecasting sources.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Copeland L (2014) Exchange rates & international finance, 6th edn. Trans-Atlantic Publications, Philadelphia

    Google Scholar 

  2. Margin(finance). Wikipedia, http://en.wikipedia.org/wiki/Margin_%28finance%29

  3. Hanif A, Smith RE (2012) Algorithmic, electronic, and automated trading. J Trading 7(4):78–86. https://doi.org/10.3905/jot.2012.7.4.078

    Article  Google Scholar 

  4. Trader. Wikipedia, http://en.wikipedia.org/wiki/Trader_(finance)

  5. Kumiega A, Vliet BEV (2012) Automated finance: the assumptions and behavioral aspects of algorithmic trading. J Behav Finance 13:51–55

    Article  Google Scholar 

  6. Taylor MP, Allen H (1992) The use of technical analysis in the foreign exchange market. J Int Money Finance 11:304–314

    Article  Google Scholar 

  7. Livingstone DJ (2009) Artificial neural networks: methods and applications. Humana Press, Totowa

    Book  Google Scholar 

  8. Zafeiriou T, Kalles D (2013) Short-term trend prediction of foreign exchange rates with a neural-network based ensemble of financial technical indicators. Int J Artif Intell Tools 22(3):1350016. https://doi.org/10.1142/S0218213013500164

    Article  Google Scholar 

  9. Hirshleifer D, Hong Teoh S, (2003) Herd Behaviour and Cascading in Capital Markets: a Review and Synthesis. Eur Financ Manag 9: 25–66. https://doi.org/10.1111/1468-036X.00207 

    Article  Google Scholar 

  10. Ruta D (2014) Automated trading with machine learning on big data. In: 2014 IEEE international congress on big data, Anchorage, AK, 2014, pp 824–830. https://doi.org/10.1109/BigData.Congress.2014.143

  11. Bunn DW (1992) Non-traditional methods of forecasting. Eur J Oper Res 92:528–536

    Article  MATH  Google Scholar 

  12. Aladaga CH, Yolcu U, Egrioglu E, Dalar AZ (2012) A new time invariant fuzzy time series forecasting method based on particle swarm optimization. Appl Soft Comput 12(10):3291–3299

    Article  Google Scholar 

  13. Zhang YQ, Wan X (2007) Statistical fuzzy interval neural networks for currency exchange rate time series forecasting. Appl Soft Comput 7:1149–1156

    Article  Google Scholar 

  14. Septiawan FY, Hayati A, Kusuma H (2017) Forecasting of currency exchange rate in forex trading system using genetic algorithm. In: International interdisciplinary conference on science technology machineering management pharmacy and humanities held

  15. Venugopal V, Baets W (1994) Neural networks and statistical techniques in marketing research: an conceptual comparison. Mark Intell Plan 12:30–38

    Article  Google Scholar 

  16. Chavarnakul Th, Enke D (2008) Intelligent technical analysis based equivolume charting for stock trading using neural networks. Expert Syst Appl 34:1004–1017

    Article  Google Scholar 

  17. Yong YL, Ngo DCL, Lee Y (2015) Technical indicators for forex forecasting: a preliminary study. In: Advances in swarm and computational intelligence, pp 87–97

  18. Abraham A, Chowdhury MU, Petrovic-Lazarevic S (2003) Australian forex market analysis using connectionist models. Manag J Manag Theory Pract 29:18–22

    Google Scholar 

  19. Wang S, Tang Z, Chai B (2016) Exchange rate forecasting model analysis based on improved artificial neural network algorithm. In: IEEE international conference on communication systems and network technologies

  20. Vanstone B, Finnie G (2009) An empirical methodology for developing stock market trading systems using artificial neural networks. Expert Syst Appl 36:6668–6680

    Article  Google Scholar 

  21. Ni H, Yin H (2009) Exchange rate forecasting using hybrid neural networks and trading indicators. Neurocomputing 72:2815–2823

    Article  Google Scholar 

  22. Rodríguez-González A, García-Crespo Á, Colomo-Palacios R, Iglesias FG, Gómez-Berbís JM (2011) CAST: using neural networks to improve trading systems based on technical analysis by means of the RSI financial indicator. Expert Syst Appl (Article in Press)

  23. Vargas M, Anjos C, Bichara G, Evsukoff A (2018) Deep leaming for stock market prediction using technical indicators and financial news articles. In: International joint conference on neural networks (IJCNN)

  24. Khirbat G et al (2013) Optimal neural network architecture for stock market forecasting. In: IEEE international conference on communication systems and network technologies

  25. Sermpins K, Theofilatos K, Karanthanpoulos A, Georgopoulos EF, Dunis C (2013) Forecasting foreign exchange rates with adaptive neural networks using radial basis functions and particle swarm optimization. Eur J Oper Res 225:528–540

    Article  MathSciNet  MATH  Google Scholar 

  26. Nuti G, Mirghaemi M, Treleaven P, Yingsaeree C (2011) Algorithmic trading. Computer 44:61–69

    Article  Google Scholar 

  27. Zafeiriou T, Kalles D (2020) Intraday ultra-short-term forecasting of foreign exchange rates using an ensemble of neural networks based on conventional technical indicators. In: 11th Hellenic conference on artificial intelligence (SETN 2020). Association for Computing Machinery, New York, NY, USA, pp 224–231. https://doi.org/10.1145/3411408.3411418

  28. TrueFX, www.truefx.com

  29. Integral, www.integral.com.

  30. Fundora J (2020) Multiple time frames can multiply returns. Investopedia, https://www.investopedia.com /articles/trading/07/timeframes.asp#what-time-frames-should-you-be-tracking

  31. Shynkevich Y, McGinnity TM, Coleman SA, Belatreche A, Li Y (2017) Forecasting price movements using technical indicators: investigating the impact of varying input window length. Neurocomputing 264:71–78

    Article  Google Scholar 

  32. Tick, Investopedia. http://www.investopedia.com/terms/t/tick.asp

  33. Long/Short Equity, Investopedia, http://www.investopedia.com/terms/l/long-shortequity.asp

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Theodoros Zafeiriou.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Appendices

Appendix 1: Parameterization of system

1.1 Simulators of moving averages

Conditions

Trend forecasting signal

MA_Μ(t) < MA_10(t) && MA_Μ(t-1) ≥ MA_10(t-1)

+ 1

MA_Μ(t) > MA_10(t) && MA_Μ(t-1) ≤ MA_10(t-1)

− 1

MA_Μ(t) < MA_10(t)

+ 0.5

MA_Μ(t) > MA_10(t)

− 0.5

Other cases

0

  1. MA_M(t): Moiving Average of M values, MA_10: Moving Average of 10- values

1.2 Oscillators simulators

 

Trend forecasting signal

Conditions of CCI

CCI(t) < -150 && CCI(t) < CCI(t-1) && CCI(t-1) < CCI(t-2) && CCI(t-2) < CCI(t-3)

+ 2

CCI(t) > 150 && CCI(t) > CCI(t-1) && CCI(t-1) > CCI(t-2) && CCI(t-2) > CCI(t-3)

− 2

CCI(t) < -150

+ 1.5

CCI(t) > 150

− 1.5

CCI(t) < -100

+ 1

CCI(t) > 100

− 1

CCI(t) < CCI(t-1) && CCI(t-1) < CCI(t-2) && CCI(t) < 0

+ 0.5

CCI(t) > CCI(t-1) && CCI(t-1) > CCI(t-2) && CCI(t) > 0

− 0.5

Other cases

0

Conditions of Williams

WILL(t) < -99 && WILL(t) < WILL(t-1) && WILL(t-1) < WILL(t-2) && WILL(t-2) < WILL(t-3)

+ 2

WILL(t) > -1 && WILL(t) > WILL(t-1) && WILL(t-1) > WILL(t-2) && WILL(t-2) > WILL(t-3)

− 2

WILL(t) < -99

+ 1.5

WILL(t) > -1

− 1.5

WILL(t) < -98

+ 1

WILL(t) > -2

− 1

WILL(t) < -80

+ 0.5

WILL(t) > -20

− 0.5

Other cases

0

Conditions of RSI

RSI(t) < 5 && RSI(t) < RSI(t-1) && RSI(t-1) < RSI(t-2) && RSI(t-2) < RSI(t-3)

+ 2

RSI(t) > 90 && RSI(t) > RSI(t-1) && RSI(t-1) > RSI(t-2) && RSI(t-2) > RSI(t-3)

− 2

RSI(t) < 5

+ 1.5

RSI(t) > 90

− 1.5

RSI(t) < 15

+ 1

RSI(t) > 85

− 1

RSI(t) < 30

+ 0.5

RSI(t) > 70

− 0.5

Other cases

0

Conditions of price oscillator

PROSC(t) < -12

+ 2

PROSC(t) > 12

− 2

PROSC(t) < -9

+ 1.5

PROSC(t) > 9

− 1.5

PROSC(t) < 6

+ 1

PROSC(t) > -6

− 1

PROSC(t) < 0

+ 0.5

PROSC(t) > 0

− 0.5

Other cases

0

1.3 Content of the system's configuration file

Line

Parameter

Value

1st

Number of ANN epochs

10

2nd

Number of ANN Hidden Neurons

14

3rd

Learning rates between synapses of Neurons of Hidden Layer with Input Neurons (LR-Inputs)

0.001

4th

Learning rates between synapses of Neurons of Hidden Layer with Output Neurons (LR-Output)

0.001

5th

Number of ΑΝΝ Hidden layers

1

6th

Number of Exit Neurons

1

7th

Number of Import Neurons

7

8th

Period (in a number of values) of Oscillator RSI

600

9th

Period (ιn a number of values) of Oscillator Williams

600

10th

Period (ιn a number of values) of Oscillator CCI

600

11th

Period (ιn a number of values) of Short-Term MA

600

12th

Period (ιn a number of values) of Mid-Term MA

900

13th

Period (ιn a number of values) of Long-Term MA

1800

14th

Period (ιn a number of values) of auxiliary MA (used instead of a pair of instantaneous values so that there is no possible momentary deviation of values due to tick to tick data)

10

15th

Number of ANN pairs

3

16th

M(x) (In a number of prices approx. 1price = 1 sec)

30

17th

Trend Value ± 2

1.00090

18th

Trend Value ± 1.5

1.00060

19th

Trend Value ± 1

1.00030

20th

Trend Value ± 0.5

1.00015

21th

a(x)

0,5

22th

Number of Αutomated Trading Machines

32

23th

Machine Sensitivity (1000–0). Paragraph 3.4.1

1

24th

Machine Class. Paragraph 3.4.1

0

25th

Take Profit Factor for trend signals of very high intensity ± 2. Paragraph. 3.4.1

1.00090

26th

Take Profit Factor for trend signals of high intensity ± 1.5. Paragraph. 3.4.1

1.00060

27th

Take Profit Factor for trend signals of normal intensity ± 1. Paragraph. 3.4.1

1.00030

28th

Stop Loss Factor. Paragraph. 3.4.1

1.0012

29th

Revision Time of take profit factors. Paragraph. 3.4.1

60

30th

Maximum Waiting Time. Paragraph. 3.4.1

120

31th

Revised Take Profit Factor. Paragraph. 3.4.1

1

32th

Source of Trend Forecasting Signals (0 έως 7). Paragraph. 3.4.1

0

33th

Total Investment Capital

$ 10,000

34th

Capital per Transaction

$ 10,000

  1. Lines 16 through 21 are repeated as many times as the number of ANN pairs as set on the 15th line
  2. Lines 23 through 34 are repeated as many times as the number of machines as set on the 22th line. So each machine has its own exclusive parameterization

Appendix 2: Analytical results of experimentation per day, machine and source of forecast (July, August and September 2020)

 

1-Jul

2-Jul

3-Jul

5-Jul

6-Jul

7-Jul

8-Jul

9-Jul

10-Jul

12-Jul

13-Jul

14-Jul

15-Jul

Type III (ANN)

− 6

71

− 55

4

15

10

23

88

5

0

88

− 29

53

Type I (ANN)

− 31

530

− 331

2

276

− 123

158

617

90

0

419

− 15

448

Type IV (ANN)

− 6

77

− 55

4

16

10

14

93

5

0

88

− 29

53

Type II (ANN)

− 31

541

− 331

2

279

− 123

149

620

90

0

419

− 15

448

Type III (PROSC)

− 261

− 483

− 261

− 31

− 294

− 123

− 553

− 287

− 298

− 89

14

− 316

− 306

Type I (PROSC)

− 2523

− 3860

− 2230

− 182

− 2558

− 594

− 5041

− 2234

− 3005

− 858

856

− 2168

− 2079

Type IV (PROSC)

− 261

− 483

− 261

− 31

− 294

− 123

− 553

− 287

− 298

− 89

14

− 316

− 306

Type II (PROSC)

− 2523

− 3860

− 2230

− 182

− 2558

− 594

− 5041

− 2234

− 3005

− 858

856

− 2168

− 2079

Type III (CCI)

− 664

− 950

− 483

− 23

− 707

− 564

− 921

− 702

− 386

− 270

− 1016

− 533

− 684

Type I (CCI)

− 5507

− 7825

− 3878

− 135

− 6321

− 4287

− 8524

− 5510

− 3174

− 2432

− 8512

− 4264

− 6156

Type IV (CCI)

− 691

− 963

− 629

− 23

− 703

− 591

− 946

− 709

− 388

− 270

− 1036

− 600

− 755

Type II (CCI)

− 5602

− 7835

− 4736

− 135

− 6305

− 4444

− 8613

− 5525

− 3158

− 2438

− 8607

− 4581

− 6274

Type III (WILL)

− 138

− 178

− 259

1

− 291

− 271

− 295

− 181

− 114

− 83

− 260

− 176

− 237

Type I (WILL)

− 706

− 895

− 1071

13

− 1647

− 702

− 1437

− 720

− 614

− 351

− 863

− 956

− 1297

Type IV (WILL)

− 138

− 176

− 279

1

− 290

− 275

− 295

− 181

− 114

− 83

− 265

− 224

− 239

Type II (WILL)

− 712

− 893

− 1124

13

− 1646

− 719

− 1437

− 720

− 613

− 351

− 868

− 1042

− 1303

Type III (RSI)

− 178

− 401

− 136

− 1

− 36

− 56

− 252

− 252

− 20

− 109

− 110

− 250

− 123

Type I (RSI)

− 877

− 3038

− 366

− 6

296

− 169

− 1626

− 1674

− 74

− 719

− 324

− 1379

− 269

Type IV (RSI)

− 178

− 401

− 136

− 1

− 36

− 56

− 252

− 252

− 20

− 109

− 110

− 250

− 123

Type II (RSI)

− 877

− 3038

− 366

− 6

296

− 169

− 1626

− 1674

− 74

− 719

− 324

− 1379

− 269

Type III (MA600)

− 83

− 30

− 142

− 5

− 82

− 144

− 46

− 73

− 63

− 7

− 68

− 92

− 71

Type I (MA600)

− 83

− 30

− 142

− 5

− 82

− 144

− 46

− 73

− 63

− 7

− 68

− 92

− 71

Type IV (MA600)

− 148

− 134

− 202

− 3

− 140

− 183

− 76

− 119

− 96

− 7

− 209

− 193

− 128

Type II (MA600)

− 148

− 134

− 202

− 3

− 140

− 183

− 76

− 119

− 96

− 7

− 209

− 193

− 128

Type III (MA900)

− 76

− 40

− 108

− 3

− 78

− 93

− 60

− 45

− 39

− 9

− 25

− 68

− 98

Type I (MA900)

− 76

− 40

− 108

− 3

− 78

− 93

− 60

− 45

− 39

− 9

− 25

− 68

− 98

Type IV (MA900)

− 109

− 82

− 157

− 2

− 109

− 286

− 77

− 113

− 87

− 9

− 70

− 112

− 132

Type II (MA900)

− 109

− 82

− 157

− 2

− 109

− 286

− 77

− 113

− 87

− 9

− 70

− 112

− 132

Type III (MA1800)

− 38

− 33

− 121

− 13

− 37

− 22

− 60

− 38

− 27

− 5

− 56

− 96

− 89

Type I (MA1800)

− 38

− 33

− 121

− 13

− 37

− 22

− 60

− 38

− 27

− 5

− 56

− 96

− 89

Type IV (MA1800)

− 58

− 69

− 169

− 21

− 54

− 27

− 96

− 53

− 43

− 7

− 125

− 100

− 184

Type II (MA1800)

− 58

− 69

− 169

− 21

− 54

− 27

− 96

− 53

− 43

− 7

− 125

− 100

− 184

 

16-Jul

17-Jul

19-Jul

20-Jul

21-Jul

22-Jul

23-Jul

24-Jul

25-Jul

26-Jul

27-Jul

29-Jul

30-Jul

31-Jul

Type III (ANN)

23

0

− 72

55

− 21

46

− 19

− 67

3

28

76

101

− 126

27

Type I (ANN)

274

− 4

− 494

322

− 292

85

− 21

− 378

− 2

− 141

217

1220

− 1085

257

Type IV (ANN)

23

0

− 69

55

− 25

42

− 18

− 67

9

30

77

105

− 128

27

Type II (ANN)

274

− 4

− 478

321

− 302

68

− 14

− 380

13

− 138

219

1223

− 1216

248

Type III (PROSC)

− 732

− 257

− 214

− 410

− 594

6

− 151

60

− 159

− 1088

− 794

− 540

− 524

− 674

Type I (PROSC)

− 6148

− 2324

− 2208

− 2862

− 4966

410

− 821

618

− 1585

− 8777

− 6487

− 4765

− 4705

− 6470

Type IV (PROSC)

− 732

− 257

− 214

− 410

− 594

6

− 151

60

− 159

− 1088

− 794

− 540

− 524

− 674

Type II (PROSC)

− 6148

− 2324

− 2208

− 2862

− 4966

410

− 821

618

− 1585

− 8777

− 6487

− 4765

− 4705

− 6469

Type III (CCI)

− 1214

− 449

− 228

− 820

− 1001

− 670

− 978

− 713

− 199

− 1698

− 1344

− 857

− 1439

− 1012

Type I (CCI)

− 10,503

− 3867

− 1879

− 7284

− 9093

− 5560

− 8352

− 5260

− 1839

− 14,809

− 11,650

− 6473

− 12,374

− 8450

Type IV (CCI)

− 1219

− 451

− 228

− 853

− 1050

− 682

− 1094

− 750

− 228

− 1872

− 1337

− 858

− 1460

− 1004

Type II (CCI)

− 10,550

− 3944

− 1879

− 7498

− 9226

− 5675

− 8973

− 5379

− 1885

− 15,552

− 11,660

− 6445

− 12,406

− 8452

Type III (WILL)

− 501

− 174

− 99

− 137

− 448

− 207

− 342

− 42

− 57

− 700

− 377

− 212

− 471

− 218

Type I (WILL)

− 1911

− 711

− 668

− 781

− 2106

− 727

− 1925

− 63

− 106

− 3403

− 1955

− 956

− 2342

− 764

Type IV (WILL)

− 501

− 174

− 99

− 137

− 480

− 212

− 456

− 42

− 57

− 744

− 378

− 212

− 471

− 218

Type II (WILL)

− 1911

− 711

− 668

− 782

− 2137

− 734

− 2243

− 63

− 106

− 3447

− 1956

− 965

− 2342

− 760

Type III (RSI)

− 434

− 32

− 73

− 7

22

− 175

− 315

− 10

− 38

− 418

− 601

− 325

− 183

− 238

Type I (RSI)

− 3175

48

− 481

526

440

− 1433

− 1697

− 3

− 21

− 2009

− 3817

− 2196

− 642

− 802

Type IV (RSI)

− 434

− 32

− 73

− 7

22

− 175

− 315

− 10

− 38

− 418

− 601

− 325

− 183

− 238

Type II (RSI)

− 3175

48

− 481

526

440

− 1433

− 1697

− 3

− 21

− 2009

− 3817

− 2196

− 642

− 802

Type III (MA600)

− 98

− 40

− 2

− 116

− 3

− 10

− 89

− 75

− 92

− 82

− 80

− 90

− 48

− 61

Type I (MA600)

− 98

− 40

− 2

− 116

− 3

− 10

− 89

− 75

− 92

− 82

− 80

− 90

− 48

− 61

Type IV (MA600)

− 216

− 93

4

− 155

− 63

− 153

− 141

− 135

− 114

− 164

− 230

− 200

− 95

− 115

Type II (MA600)

− 216

− 93

4

− 155

− 63

− 153

− 141

− 135

− 114

− 164

− 230

− 200

− 95

− 115

Type III (MA900)

− 89

− 28

− 4

− 112

− 68

− 26

− 37

− 55

− 69

− 85

− 128

− 85

− 46

− 62

Type I (MA900)

− 89

− 28

− 4

− 112

− 68

− 26

− 37

− 55

− 69

− 85

− 128

− 85

− 46

− 62

Type IV (MA900)

− 151

− 64

− 3

− 119

− 116

− 55

− 88

− 91

− 70

− 158

− 154

− 146

− 94

− 123

Type II (MA900)

− 151

− 64

− 3

− 119

− 116

− 55

− 88

− 91

− 70

− 158

− 154

− 146

− 94

− 123

Type III (MA1800)

− 43

− 35

4

− 79

− 9

− 8

− 19

− 19

− 17

− 100

− 53

− 109

− 12

− 22

Type I (MA1800)

− 43

− 35

4

− 79

− 9

− 8

− 19

− 19

− 17

− 100

− 53

− 109

− 12

− 22

Type IV (MA1800)

− 121

− 53

4

− 131

− 36

− 39

− 57

− 32

− 29

− 144

− 63

− 131

− 61

− 76

Type II (MA1800)

− 121

− 53

4

− 131

− 36

− 39

− 57

− 32

− 29

− 144

− 63

− 131

− 61

− 76

 

2-Aug

3-Aug

4-Aug

5-Aug

6-Aug

7-Aug

9-Aug

10-Aug

11-Aug

12-Aug

13-Aug

14-Aug

16-Aug

Type III (ANN)

3

168

116

136

295

209

12

49

150

135

114

90

16

Type I (ANN)

16

1088

765

842

1948

1362

72

283

830

733

616

598

138

Type IV (ANN)

3

171

116

141

314

217

12

50

154

139

115

93

18

Type II (ANN)

16

1096

766

865

2014

1395

72

284

836

741

617

601

145

Type III (PROSC)

38

1233

1093

1205

1465

946

17

798

1466

1035

982

703

21

Type I (PROSC)

360

11,452

10,185

11,176

13,732

8800

152

7332

13,504

9369

8933

6514

157

Type IV (PROSC)

38

1233

1093

1205

1465

946

17

798

1466

1035

982

703

21

Type II (PROSC)

360

11,452

10,185

11,176

13,732

8800

152

7332

13,504

9369

8933

6514

157

Type III (CCI)

35

2005

2123

1959

2202

1956

65

1674

2241

2059

1950

1679

79

Type I (CCI)

325

17,483

18,766

17,305

19,211

16,651

443

14,638

19,569

17,777

16,922

14,605

688

Type IV (CCI)

35

2012

2138

1964

2210

1986

75

1686

2256

2077

1969

1703

88

Type II (CCI)

325

17,524

18,853

17,328

19,247

16,798

481

14,691

19,640

17,852

17,005

14,738

728

Type III (WILL)

9

618

660

671

702

544

16

560

716

660

608

477

29

Type I (WILL)

46

3095

3364

3454

3714

2698

56

2696

3722

3301

3077

2370

125

Type IV (WILL)

9

618

662

671

702

544

18

561

717

661

608

479

32

Type II (WILL)

9

618

662

671

702

544

18

561

717

661

608

479

32

Type III (RSI)

3

511

640

587

733

415

534

744

460

469

391

23

432

Type I (RSI)

12

3514

4354

4110

5533

2712

3907

5226

2933

3102

2863

155

3181

Type IV (RSI)

3

511

640

587

733

415

534

744

460

469

391

23

432

Type II (RSI)

3

511

640

587

733

415

534

744

460

469

391

23

432

Type III (MA600)

2

184

160

162

181

223

11

131

170

181

173

139

6

Type I (MA600)

2

184

160

162

181

223

11

131

170

181

173

139

6

Type IV (MA600)

2

312

256

263

294

380

19

209

276

291

281

235

10

Type II (MA600)

2

312

256

263

294

380

19

209

276

291

281

235

10

Type III (MA900)

1

138

139

128

132

188

6

104

135

163

120

102

4

Type I (MA900)

1

138

139

128

132

188

6

104

135

163

120

102

4

Type IV (MA900)

1

225

226

207

214

322

9

161

222

257

195

167

6

Type II (MA900)

1

225

226

207

214

322

9

161

222

257

195

167

6

Type III (MA1800)

3

82

88

94

93

108

12

79

94

115

94

117

5

Type I (MA1800)

3

82

88

94

93

108

12

79

94

115

94

117

5

Type IV (MA1800)

5

132

145

154

147

184

19

131

150

181

160

202

8

Type II (MA1800)

5

132

145

154

147

184

19

131

150

181

160

202

8

 

17-Aug

18-Aug

19-Aug

20-Aug

21-Aug

23-Aug

24-Aug

25-Aug

26-Aug

27-Aug

28-Aug

30-Aug

31-Aug

Type III (ANN)

57

136

165

182

158

16

57

84

87

374

200

12

97

Type I (ANN)

268

828

1161

1108

1051

69

281

498

540

2617

1229

75

631

Type IV (ANN)

58

142

174

186

159

17

58

85

87

403

210

12

98

Type II (ANN)

270

839

1211

1119

1054

72

282

499

540

2768

1259

75

635

Type III (PROSC)

647

891

910

1034

953

17

549

857

805

1505

1259

34

717

Type I (PROSC)

5954

4030

910

1034

953

17

549

857

805

1505

1259

34

717

Type IV (PROSC)

647

891

910

1034

953

17

549

857

805

1505

1259

34

717

Type II (PROSC)

5954

8202

8227

9506

8685

122

4753

7689

7378

14,181

11,573

320

6395

Type III (CCI)

1603

1793

1958

2155

1818

79

1571

1929

1832

2162

2107

118

1891

Type I (CCI)

13,993

15,651

17,071

18,901

15,697

696

13,723

16,925

15,950

18,966

18,555

933

16,140

Type IV (CCI)

1623

1813

1965

2167

1838

80

1603

1938

1851

2179

2117

128

1914

Type II (CCI)

14,120

15,750

17,125

18,966

15,809

698

13,886

16,983

16,055

19,073

18,623

998

16,258

Type III (WILL)

507

555

550

691

590

26

495

593

581

691

643

46

596

Type I (WILL)

2633

2715

2749

3405

2891

154

2369

2896

3048

3494

3252

216

2917

Type IV (WILL)

507

555

551

693

592

26

497

593

582

693

643

49

598

Type II (WILL)

507

555

551

693

592

26

497

593

582

693

643

49

598

Type III (RSI)

409

394

610

476

12

407

457

530

652

613

13

501

11,016

Type I (RSI)

2592

2573

4093

3293

40

2768

2955

3809

4612

4215

85

3560

76,197

Type IV (RSI)

409

394

610

476

12

407

457

530

652

613

13

501

11,016

Type II (RSI)

409

394

610

476

12

407

457

530

652

613

13

501

11,016

Type III (MA600)

144

152

182

188

138

7

134

147

183

209

190

12

187

Type I (MA600)

144

152

182

188

138

7

134

147

183

209

190

12

187

Type IV (MA600)

228

234

297

309

219

12

213

239

317

356

312

18

311

Type II (MA600)

228

234

297

309

219

12

213

239

317

356

312

18

311

Type III (MA900)

126

144

160

142

123

3

125

115

132

163

169

19

145

Type I (MA900)

126

144

160

142

123

3

125

115

132

163

169

19

145

Type IV (MA900)

202

228

267

225

201

4

207

177

229

270

282

30

239

Type II (MA900)

202

228

267

225

201

4

207

177

229

270

282

30

239

Type III (MA1800)

111

128

105

106

81

6

83

90

69

97

80

5

89

Type I (MA1800)

111

128

105

106

81

6

83

90

69

97

80

5

89

Type IV (MA1800)

182

208

169

167

130

9

137

136

114

160

132

10

138

Type II (MA1800)

182

208

169

167

130

9

137

136

114

160

132

10

138

 

1-Sep

2-Sep

3-Sep

4-Sep

6-Sep

7-Sep

8-Sep

9-Sep

10-Sep

11-Sep

13-Sep

14-Sep

15-Sep

Type III (ANN)

163

144

137

170

4

12

181

112

271

70

13

28

62

Type I (ANN)

1062

824

756

1030

25

57

1075

668

1707

470

105

145

383

Type IV (ANN)

166

149

138

180

4

12

187

119

290

70

14

29

63

Type II (ANN)

1067

837

757

1073

25

57

1123

695

1784

470

114

149

384

Type III (PROSC)

1247

1157

1041

794

13

258

973

624

871

583

49

368

392

Type I (PROSC)

11,555

10,599

9448

7129

47

2362

8999

5418

7802

5246

430

3091

3563

Type IV (PROSC)

1247

1157

1041

794

13

258

973

624

871

583

49

368

392

Type II (PROSC)

11,555

10,599

9448

7129

47

2362

8999

5418

7802

5246

430

3091

3563

Type III (CCI)

1996

2041

2067

1932

98

1237

1968

1818

1995

1637

56

1546

785

Type I (CCI)

17,516

17,813

17,898

16,917

661

10,366

17,121

15,822

16,954

14,318

533

13,215

6681

Type IV (CCI)

2005

2050

2082

1942

113

1262

1984

1843

2016

1658

57

1558

1651

Type II (CCI)

17,569

17,857

17,980

16,971

695

10,489

17,220

15,944

17,102

14,413

536

13,243

7630

Type III (WILL)

652

688

576

562

21

371

598

476

534

479

25

464

485

Type I (WILL)

3407

3491

2925

2823

103

1810

2891

2413

2674

2272

127

2251

2328

Type IV (WILL)

652

688

577

562

23

372

598

476

534

479

25

464

485

Type II (WILL)

3408

3491

2927

2823

108

1812

2891

2413

2674

2272

127

2251

2329

Type III (RSI)

593

517

489

440

14

321

486

325

440

420

30

351

254

Type I (RSI)

4129

3342

3312

3046

65

1960

3380

2096

2977

2925

209

2148

1455

Type IV (RSI)

593

517

489

440

14

321

488

325

440

420

30

351

254

Type II (RSI)

4129

3342

3312

3046

65

1960

3387

2096

2977

2925

209

2148

1455

Type III (MA600)

179

162

186

197

16

149

208

190

204

150

3

133

182

Type I (MA600)

179

162

186

197

16

149

208

190

204

150

3

133

182

Type IV (MA600)

289

264

294

324

24

247

342

315

330

233

3

220

300

Type II (MA600)

289

264

294

324

24

247

342

315

330

233

3

220

300

Type III (MA900)

151

157

158

147

21

124

159

152

159

138

5

97

129

Type I (MA900)

151

157

158

147

21

124

159

152

159

138

5

97

129

Type IV (MA900)

243

259

258

238

32

205

262

255

256

221

7

154

206

Type II (MA900)

243

259

258

238

32

205

262

255

256

221

7

154

206

Type III (MA1800)

93

112

80

93

10

93

95

124

119

99

6

69

96

Type I (MA1800)

93

112

80

93

10

93

95

124

119

99

6

69

96

Type IV (MA1800)

149

185

134

142

12

159

156

211

199

162

9

115

155

Type II (MA1800)

149

185

134

142

12

159

156

211

199

162

9

115

155

 

16-Sep

17-Sep

18-Sep

20-Sep

21-Sep

22-Sep

23-Sep

24-Sep

25-Sep

27-Sep

28-Sep

29-Sep

30-Sep

Type III (ANN)

223

155

38

6

123

155

119

115

64

18

70

94

138

Type I (ANN)

1290

955

231

37

716

979

770

753

361

105

419

608

779

Type IV (ANN)

244

159

38

6

124

160

120

118

65

18

70

95

142

Type II (ANN)

1396

975

231

37

722

994

772

764

363

105

419

609

794

Type III (PROSC)

1181

1172

507

8

927

1107

894

972

533

84

616

773

1106

Type I (PROSC)

10,880

10,591

4501

29

8687

9860

8046

8819

4793

785

5476

7128

10,146

Type IV (PROSC)

1181

1172

507

8

927

1107

894

972

533

84

616

773

1106

Type II (PROSC)

10,880

10,591

4501

29

8687

9860

8046

8819

4793

785

5476

7128

10,146

Type III (CCI)

10,880

10,591

4501

29

8687

9860

8046

8819

4793

785

5476

7128

10,146

Type I (CCI)

10,880

10,591

4501

29

8687

9860

8046

8819

4793

785

5476

7128

10,146

Type IV (CCI)

1839

2230

1759

76

1989

2123

2131

2188

1735

80

1713

1673

2172

Type II (CCI)

1839

2230

1759

76

1989

2123

2131

2188

1735

80

1713

1673

2172

Type III (WILL)

598

695

498

14

588

656

591

640

458

43

577

529

688

Type I (WILL)

3048

3446

2429

69

2903

3126

2719

3112

2112

275

2916

2696

3604

Type IV (WILL)

598

695

499

14

589

656

593

641

458

43

578

529

690

Type II (WILL)

3051

3446

2430

69

2905

3126

2724

3115

2112

275

2917

2697

3606

Type III (RSI)

520

586

414

15

474

495

482

541

282

43

402

501

628

Type I (RSI)

3454

4133

2632

34

3173

3162

3072

3913

1798

307

2592

3362

4459

Type IV (RSI)

520

586

414

15

474

495

482

542

282

43

402

501

628

Type II (RSI)

3454

4133

2632

34

3173

3162

3072

3914

1798

307

2592

3362

4459

Type III (MA600)

170

190

156

14

182

205

172

197

161

11

170

166

180

Type I (MA600)

170

190

156

14

182

205

172

197

161

11

170

166

180

Type IV (MA600)

278

320

262

22

296

346

281

315

265

18

284

283

290

Type II (MA600)

278

320

262

22

296

346

281

315

265

18

284

283

290

Type III (MA900)

162

152

120

7

147

147

126

167

149

8

146

132

155

Type I (MA900)

162

152

120

7

147

147

126

167

149

8

146

132

155

Type IV (MA900)

272

250

196

12

244

249

193

274

245

12

244

215

260

Type II (MA900)

272

250

196

12

244

249

193

274

245

12

244

215

260

Type III (MA1800)

78

119

72

4

112

130

106

123

114

2

113

84

107

Type I (MA1800)

78

119

72

4

112

130

106

123

114

2

113

84

107

Type IV (MA1800)

124

194

118

7

183

219

173

205

190

2

184

138

177

Type II (MA1800)

124

194

118

7

183

219

173

205

190

2

184

138

177

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zafeiriou, T., Kalles, D. Ultra-short-term trading system using a neural network-based ensemble of financial technical indicators. Neural Comput & Applic 35, 35–60 (2023). https://doi.org/10.1007/s00521-021-05945-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-021-05945-4

Keywords