1 Introduction
1.1 Research proposal
1.2 Research structure
2 Research background and literature review
2.1 Genome
2.2 Artificial neural networks
2.3 Genetic algorithms
2.4 Extreme learning machine
3 The random neural network genetic deep learning model
3.1 The random neural network
- A positive spike is interpreted as excitation signal because it increases by one unit the potential of the receiving neuron;
- A negative spike is interpreted as inhibition signal decreasing by one unit the potential of the receiving neuron or has no effect if the potential is already zero.
- Positive spikes will go out to neuron j with probability p+(i, j) as excitatory signals;
- Negative spikes with probability p−(i, j) as inhibitory signals.
3.2 Reinforcement learning algorithm
- if Tl−1 ≤ R1:$$\begin{aligned} & w^{ + } \left( {i,j} \right) \, = \, w^{ + } \left( {i,j} \right) \, + \, R_{1} \\ & w^{ - } \left( {i,k} \right) \, = \, w^{ - } \left( {i,k} \right) \, + \frac{{R_{l} }}{n - 2}\quad {\text{if }}k \, \ne \, j \\ \end{aligned}$$(7)
- else if Rl < Tl−1:$$\begin{aligned} & w^{ + } \left( {i,k} \right) \, = \, w^{ + } \left( {i,k} \right) \, + \frac{{R_{l} }}{n - 2}\quad {\text{if}}\,k \, \ne \, j \\ & w^{ - } \left( {i,j} \right) \, = \, w^{ - } \left( {i,j} \right) \, + \, R_{l} \\ \end{aligned}$$(8)
3.3 The random neural network with multiple clusters
3.4 Deep learning clusters
- I = (idl1, idl2, …, idlu), a U-dimensional vector \(I \, \in \, \left[ {0,1} \right]^{U}\) that represents the input state \(\overline{{q_{u} }}\) for the cell u;
- w−(u, c) is the U × C matrix of inhibitory weights from the U input cells to the cells in each of the C clusters;
- Y = (ydl1, ydl2, …, ydlc), a C-dimensional vector \(Y \, \in \, \left[ {0,1} \right]^{C}\) that represents the cell state qc for the cluster c.
3.5 Deep learning management cluster
- Imc, a C-dimensional vector \(I_{\text{mc}} \in \left[ {0,1} \right]^{C}\) that represents the input state \(\overline{{q_{c} }}\) for the cluster c;
- w−(c) is the C-dimensional vector of inhibitory weights from the C input clusters to the cells in the management cluster mc;
- Ymc, a scalar \(Y_{\text{mc}} \in \left[ {0,1} \right]\), the cell state qmc for the management cluster mc.
3.6 Genetic learning algorithm model
- q1 = (q11, q21, …, qu1), a U-dimensional vector \(q_{1} \in \left[ {0,1} \right]^{U}\) that represents the input state qu for neuron u;
- W1 is the U × C matrix of weights w1−(u,c) from the U input neurons to the neurons in each of the C clusters;
- Q1 = (Q11, Q21, …, Qc1), a C-dimensional vector \(Q^{1} \in \left[ {0,1} \right]^{C}\) that represents state qc for the cluster c where \(Q^{1} \, = \,\zeta \left( {W_{1} X} \right)\).
- q2 = (q12, q22, …, qc2), a C-dimensional vector \(q_{2} \in \left[ {0,1} \right]^{C}\) that represents the input state qc for neuron c with the same value as Q1 = (Q11, Q21, …, Qc1);
- W2 is the C × U matrix of weights w2−(c,u) from the C input neurons to the neurons in each of the U cells;
- Q2 = (q12, q22, …, qu2), a U-dimensional vector \(Q^{2} \in \, \left[ {0,1} \right]^{U}\) that represents the state qu for the cell u where Q2 = ζ(W2Q1) or Q2 = ζ(W2ζ(XW1)).
4 Management decision structure: smart investment
4.1 Asset banker reinforcement learning
- q0, neuron 0 for a buy decision
- q1, neuron 1 for a sell decision
- if Rl > PR1:$$\begin{aligned} & {\text{Reward}}\,{\text{Buy}}\,{\text{decision:}}\,w^{ + }_{10} = \, w^{ + }_{10} + \left| R \right| \\ & {\text{or}}\,{\text{Reward}}\,{\text{Sell}}\,{\text{decision:}}\,w^{ + }_{01} = \, w^{ + }_{01} + \left| R \right| \\ \end{aligned}$$(25)
- Otherwise, if Rl < PR1:$$\begin{aligned} & {\text{Penalise}}\,{\text{Buy}}\,{\text{decision:}}\,w^{ - }_{10} = \, w^{ - }_{10} + \, \left| R \right| \\ & {\text{or}}\,{\text{Penalise}}\,{\text{Sell}}\,{\text{decision:}}\,w^{ - }_{01} = \, w^{ - }_{01} + \, \left| R \right| \\ \end{aligned}$$(26)
4.2 Asset banker deep learning cluster
- IBanker-x = (i1Banker-x, i2Banker-x, …, iuBanker-x) a U-dimensional vector where i1Banker-x, i2Banker-x, and iuBanker-x are the same banker number x;
- wBanker-x−(u, c) is the \(U \times C\) matrix of weights of the deep learning cluster for banker x;
- YBanker-x = (y1Banker-x, y2Banker-x, …, ycBanker-x) a C-dimensional vector where y1Banker-x is the reinforcement learning reward prediction, y2Banker-x is the dynamic reward prediction, y3Banker-x is the transaction price, and ycBanker-x is the price prediction for banker number x.
4.3 Market banker deep learning management cluster
- IMarketBanker-x, a C-dimensional vector \(I_{{{{\rm MarketBanker}\text{-}}x}} \in \, \left[ {0,1} \right]^{C}\) with the values of the predicted rewards from asset banker x;
- wMarketBanker-x− (c) is the C-dimensional vector of weights that represents the priority of each asset banker x;
- YMarketBanker-x, a scalar \(Y_{{{{\rm MarketBanker}\text{-}}x}} \in \, \left[ {0,1} \right]\) that represents the predicted profit the market banker deep learning management cluster can make.
4.4 CEO banker deep learning management cluster
- ICEO-Banker, a X-dimensional vector \(I_{{{{\rm CEO}}\text{-}{{\rm Banker}}}} \in \, \left[ {0,1} \right]^{X}\) with the values of the set x banker DL management clusters;
- wCEO-Banker− (c) is the C-dimensional vector of weights that represents the risk associated to each market;
- YCEO-Banker, a scalar \(Y_{{{{\rm CEO}\text{-}{\rm Banker}}}} \in \left[ {0,1} \right]\) that represents the final investment decision.
4.5 CEO banker genetic algorithm
- XGenetic = (x1Genetic, x2Genetic, …, xuGentetic) a U-dimensional vector where x1Genetic, x2Genetic, and xuGenetic are outputs of the x banker deep learning clusters;
- wGenetic−1− (u, c) is the U × C matrix of weights of the genetic encoder;
- YNucleoid = (y1Nucleoid, y2Nucleoid, …, ycNucleoid) a C-dimensional vector where y1Nucleoid, …, ycNucleoid is the value of the nucleoid
- wGenetic−2−(c, u) is the C × U matrix of weights of the genetic decoder;
- YGeneration = (y1Generation, y2Generation, …, ycGeneration) a C-dimensional vector where y1Generation, …, ycGeneration is the value of the new banker generation.
5 Smart investment implementation
5.1 Asset banker reinforcement learning and deep learning clusters
Cluster | Input | Value | Output | Value |
---|---|---|---|---|
Banker 1 | i1Banker−1 | 0.1 | y1Banker−1 | Reinforcement learning reward prediction |
Banker 1 | i2Banker−1 | 0.1 | y2Banker−1 | Dynamic reward prediction |
Banker 1 | i3Banker−1 | 0.1 | y3Banker−1 | Transaction price |
Banker 1 | i4Banker−1 | 0.1 | y4Banker−1 | Price prediction |
… | … | … | … | … |
Banker 8 | i1Banker−8 | 0.8 | y1Banker−8 | Reinforcement learning reward prediction |
Banker 8 | i1Banker−8 | 0.8 | y2Banker−8 | Dynamic reward prediction |
Banker 8 | i1Banker−8 | 0.8 | y3Banker−8 | Transaction price |
Banker 8 | i1Banker−8 | 0.8 | y4Banker−8 | Price prediction |
5.2 Market banker deep learning management clusters
Cluster | Input | Network weights | Output |
---|---|---|---|
IBondMarketBanker | wBondMarketBanker−(c) | YBondMarketBanker | |
Bond | Predicted reward banker 1 Predicted reward banker 2 Predicted reward banker 3 Predicted reward banker 4 | 0.0 1.0 0.0 0.0 | Best predicted reward bond banker |
Cluster | Input | Network weights | Output |
---|---|---|---|
IDerivativeMarketBanker | wDerivativeMarketBanker−(c) | YDerivativeMarketBanker | |
Derivative | Predicted reward banker 5 Predicted reward banker 6 Predicted reward banker 7 Predicted reward banker 8 | 0.0 1.0 0.0 0.0 | Best predicted reward derivative banker |
5.3 CEO banker deep learning management clusters
Cluster | Input | Network weight | Output |
---|---|---|---|
ICEO-Banker | wCEO-Banker− (c) | YCEO-Banker | |
CEO banker | YBondMarketBanker YDerivativeMarketBanker | 1 − β β | Predicted reward at risk β |
5.4 CEO banker genetic algorithm
Name | Variable | Value |
---|---|---|
XGenetic | x1Genetic | y1Banker−1 |
x2Genetic | y2Banker−1 | |
x3Genetic | y3Banker−1 | |
x4Genetic | y4Banker−1 | |
x5Genetic | y4Banker−2 | |
… | … | |
x8Genetic | y4Banker−2 | |
… | … | |
x32Gentetic | y4Banker−8 | |
wGenetic−1−(u,c) | wGenetic-1−(1, 1) … wGenetic-1−(32, 1) | 0.02, … 0.02 |
wGenetic-1−(1, 2) … wGenetic-1−(32, 2) | 0.15, … 0.15 | |
wGenetic-1−(1, 3) … wGenetic-1−(32, 3) | 0.40, … 0.40 | |
wGenetic-1−(1, 4) … wGenetic-1−(32, 4) | 0.99, … 0.99 | |
YNucleoid | y1Nucleoid (0.00 < C ≤ 0.25 | 0.2048 |
y2Nucleoid 0.25 < G ≤ 0.50 | 0.3900 | |
y3Nucleoid 0.50 < A ≤ 0.75 | 0.6295 | |
y4Nucleoid 0.75 < T < 0.99) | 0.9268 | |
wGenetic-2−(c,u) | wGenetic-2−(1, 1) … wGenetic-2−(1, 32) | pinv(YNucleiod)XGenetic |
wGenetic-2−(2, 1) … wGenetic-2−(2, 32) | ||
wGenetic-2−(3, 1) … wGenetic-2−(3, 32) | ||
wGenetic-2−(4, 1) … wGenetic-2−(4, 32) | ||
YGeneration | y1Generation | x1Genetic |
y2Generation | x2Genetic | |
y3Generation | x3Genetic | |
y4Generation | x4Genetic | |
y5Generation | x5Genetic | |
… | … | |
y8Generation | x8Genetic | |
… | … | |
y32Generation | x32Gentetic |
6 Smart investment experimental results
6.1 Asset banker reinforcement learning validation
Assets | Profit | Maximum profit | Ratio | Win | Loss | Buy | Sell |
---|---|---|---|---|---|---|---|
1 | 1000 | 1000 | 1.00 | 10 | 0 | 10 | 0 |
2 | 800 | 1000 | 0.80 | 9 | 1 | 1 | 9 |
3 | 600 | 600 | 1.00 | 6 | 0 | 10 | 0 |
4 | 300 | 500 | 0.60 | 4 | 1 | 6 | 4 |
5 | 2000 | 2000 | 1.00 | 8 | 0 | 4 | 6 |
6 | 1200 | 2000 | 0.60 | 6 | 2 | 4 | 6 |
7 | 1600 | 2000 | 0.80 | 9 | 1 | 6 | 4 |
8 | 800 | 2000 | 0.40 | 7 | 3 | 4 | 6 |
Asset | Profit | Maximum profit | Ratio | Win | Loss | Buy | Sell |
---|---|---|---|---|---|---|---|
1 | 1000 | 1000 | 1.00 | 10 | 0 | 10 | 0 |
2 | 800 | 1000 | 0.80 | 9 | 1 | 1 | 9 |
3 | 600 | 600 | 1.00 | 6 | 0 | 10 | 0 |
4 | 300 | 500 | 0.60 | 4 | 1 | 6 | 4 |
5 (α = 0.5) | 2000 | 2000 | 1.00 | 8 | 0 | 4 | 6 |
5 (α = 0.9) | 1600 | 2000 | 0.80 | 7 | 1 | 7 | 3 |
6 | 600 | 2000 | 0.30 | 5 | 3 | 3 | 7 |
7 | 1600 | 2000 | 0.80 | 9 | 1 | 6 | 4 |
8 | 800 | 2000 | 0.40 | 7 | 3 | 4 | 6 |
6.2 Asset banker deep learning cluster validation
Day | Asset 1 | Asset 2 | Asset 3 | Asset 4 | Asset 5 | Asset 6 | Asset 7 | Asset 8 |
---|---|---|---|---|---|---|---|---|
2 | It: 1725 | It: 983 | It: 663 | It: 519 | It: 389 | It: 416 | It: 302 | It: 337 |
E: 9.87 | E: 9.70 | E: 9.48 | E: 9.38 | E: 9.51 | E: 9.79 | E: 6.59 | E: 9.92 | |
3 | It: 1720 | It: 889 | It: 663 | It: 519 | It: 367 | It: 324 | It: 300 | It: 277 |
E: 9.73 | E: 9.74 | E: 9.48 | E: 9.38 | E: 9.86 | E: 8.10 | E: 7.90 | E: 8.81 | |
4 | It: 1720 | It: 886 | It: 663 | It: 519 | It: 366 | It: 321 | It: 299 | It: 273 |
E: 9.77 | E: 9.47 | E: 9.48 | E: 9.38 | E: 9.95 | E: 9.00 | E: 9.81 | E: 9.70 | |
5 | It: 1718 | It: 884 | It: 663 | It: 519 | It: 386 | It: 352 | It: 300 | It: 273 |
E: 9.93 | E: 9.69 | E: 9.48 | E: 9.38 | E: 7.83 | E: 9.80 | E: 7.57 | E: 9.53 | |
6 | It: 1718 | It: 884 | It: 628 | It: 519 | It: 429 | It: 373 | It: 300 | It: 287 |
E: 9.97 | E: 9.68 | E: 9.90 | E: 9.38 | E: 9.00 | E: 8.38 | E: 7.48 | E: 7.51 | |
7 | It: 1720 | It: 884 | It: 627 | It: 547 | It: 431 | It: 374 | It: 370 | It: 336 |
E: 9.83 | E: 9.16 | E: 9.10 | E: 9.26 | E: 9.81 | E: 8.78 | E: 9.33 | E: 9.77 | |
8 | It: 1720 | It: 884 | It: 627 | It: 494 | It: 388 | It: 409 | It: 303 | It: 335 |
E: 9.42 | E: 9.49 | E: 9.46 | E: 8.82 | E: 9.89 | E: 9.50 | E: 9.11 | E: 8.75 | |
9 | It: 1720 | It: 884 | It: 627 | It: 491 | It: 367 | It: 324 | It: 300 | It: 277 |
E: 9.41 | E: 9.57 | E: 9.17 | E: 8.95 | E: 9.77 | E: 8.55 | E: 8.38 | E: 9.54 | |
10 | It: 1719 | It: 886 | It: 627 | It: 491 | It: 369 | It: 319 | It: 299 | It: 274 |
E: 9.89 | E: 9.11 | E: 9.12 | E: 8.29 | E: 9.94 | E: 8.34 | E: 9.87 | E: 7.56 | |
11 | It: 1720 | It: 896 | It: 626 | It: 495 | It: 407 | It: 335 | It: 315 | It: 273 |
E: 9.74 | E: 8.21 | E: 9.55 | E: 9.99 | E: 8.76 | E: 7.38 | E: 8.07 | E: 9.83 |
6.3 Market banker deep learning management cluster validation
Day | Total asset banker | Bond market banker | I (%) | Maximum asset banker | Maximum market banker | I (%) |
---|---|---|---|---|---|---|
2 | 0 | 400 | 400.00 | 200 | 400 | 100.00 |
3 | 200 | 400 | 100.00 | 200 | 400 | 100.00 |
4 | 200 | 400 | 100.00 | 200 | 400 | 100.00 |
5 | 200 | 400 | 100.00 | 200 | 400 | 100.00 |
6 | 300 | 400 | 33.33 | 300 | 400 | 33.33 |
7 | 200 | 400 | 100.00 | 400 | 400 | 0.00 |
8 | 400 | 400 | 0.00 | 400 | 400 | 0.00 |
9 | 400 | 400 | 0.00 | 400 | 400 | 0.00 |
10 | 400 | 400 | 0.00 | 400 | 400 | 0.00 |
11 | 400 | 400 | 0.00 | 400 | 400 | 0.00 |
Total | 2700 | 4000 | 48.15 | 3100 | 4000 | 29.03 |
Day | Total asset banker | Derivative market banker | I (%) | Maximum asset banker | Maximum market banker | I (%) |
---|---|---|---|---|---|---|
2 | 0 | 800.0 | 400.00 | 800 | 800.0 | 400.00 |
3 | 1000 | 1200 | 20.00 | 1000 | 1200 | 20.00 |
4 | 1000 | 1200 | 20.00 | 1000 | 1200 | 20.00 |
5 | 800 | 800 | 0.00 | 800 | 800 | 0.00 |
6 | 400 | 0 | − 100.00 | 400 | 0 | − 100.00 |
7 | − 400 | − 800 | 100.00 | 400 | 800 | 100.00 |
8 | 0 | 800 | 800 | 800 | 800 | 0.00 |
9 | 1000 | 1200 | 20.00 | 1000 | 1200 | 20.00 |
10 | 1000 | 1200 | 20.00 | 1000 | 1200 | 20.00 |
11 | 800 | 800 | 0.00 | 800 | 800 | 0.00 |
Total | 5600 | 7200 | 28.57 | 8000 | 8800 | 10.00 |
Day | IBondMarketBanker | wBondMarketBanker−(c) | YBondMarketBanker | ||||||
---|---|---|---|---|---|---|---|---|---|
2 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.0 | 0.0 | 0.0 | 0.0 | 0.9994 |
3 | 0.5090 | 0.4910 | 0.5000 | 0.5000 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5146 |
4 | 0.5100 | 0.5081 | 0.5000 | 0.5000 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5142 |
5 | 0.5100 | 0.5098 | 0.5000 | 0.5000 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5142 |
6 | 0.5100 | 0.5100 | 0.5000 | 0.5000 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5142 |
7 | 0.5100 | 0.5100 | 0.5090 | 0.5000 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5142 |
8 | 0.5100 | 0.5100 | 0.5099 | 0.4910 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5142 |
9 | 0.5100 | 0.5100 | 0.5100 | 0.5081 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5142 |
10 | 0.5100 | 0.5100 | 0.5100 | 0.5098 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5142 |
11 | 0.5100 | 0.5100 | 0.5100 | 0.5100 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5142 |
Day | IDerivativeMarketBanker | wDerivativeMarketBanker−(c) | YDerivativeMarketBanker | ||||||
---|---|---|---|---|---|---|---|---|---|
2 | 0.0000 | 0.0000 | 0.0000 | 0.0000 | 1.0 | 0.0 | 0.0 | 0.0 | 0.9994 |
3 | 0.5180 | 0.4820 | 0.5180 | 0.4820 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5103 |
4 | 0.5288 | 0.5252 | 0.5198 | 0.5162 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5051 |
5 | 0.5299 | 0.5295 | 0.5200 | 0.5196 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5046 |
6 | 0.5210 | 0.5210 | 0.5200 | 0.5200 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5088 |
7 | 0.5021 | 0.5021 | 0.5200 | 0.5200 | 0.0 | 0.0 | 1.0 | 0.0 | 0.5093 |
8 | 0.5002 | 0.5002 | 0.4840 | 0.4840 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5190 |
9 | 0.5180 | 0.4820 | 0.5164 | 0.4804 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5103 |
10 | 0.5288 | 0.5252 | 0.5196 | 0.5160 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5051 |
11 | 0.5299 | 0.5295 | 0.5200 | 0.5196 | 1.0 | 0.0 | 0.0 | 0.0 | 0.5046 |
6.4 CEO banker deep learning management cluster validation
Day | Risk β = 0.2 | Risk β = 0.5 | Risk β = 0.8 | Max profit | ||||||
---|---|---|---|---|---|---|---|---|---|---|
B | D | Total | B | D | Total | B | D | Total | ||
2 | 640 | 320 | 960 | 400 | 800 | 1200 | 160 | 1280 | 1440 | 1440 |
3 | 640 | 480 | 1120 | 400 | 1200 | 1600 | 160 | 1920 | 2080 | 2080 |
4 | 640 | 480 | 1120 | 400 | 1200 | 1600 | 160 | 1920 | 2080 | 2080 |
5 | 640 | 320 | 960 | 400 | 800 | 2800 | 160 | 1280 | 1440 | 1440 |
6 | 640 | 0 | 640 | 400 | 0 | 400 | 160 | 0 | 160 | 640 |
7 | 640 | − 320 | 320 | 400 | − 800 | − 400 | 160 | − 1280 | − 1120 | 320 |
8 | 640 | 320 | 960 | 400 | 800 | 1200 | 160 | 1280 | 1440 | 1440 |
9 | 640 | 480 | 1120 | 400 | 1200 | 1600 | 160 | 1920 | 2080 | 2080 |
10 | 640 | 480 | 1120 | 400 | 1200 | 1600 | 160 | 1920 | 2080 | 2080 |
11 | 640 | 640 | 1280 | 400 | 800 | 1200 | 160 | 1280 | 1440 | 1440 |
Total | 6400 | 3200 | 9600 | 4000 | 7200 | 12,800 | 1600 | 11,520 | 13,120 | 15,040 |
Day | ICEO-Banker | Risk β = 0.2 | Risk β = 0.5 | Risk β = 0.8 | ||||
---|---|---|---|---|---|---|---|---|
YCEO-Banker | D | YCEO-Banker | D | YCEO-Banker | D | |||
2 | 0.9994 | 0.9994 | 0.2127 | 0.1 | 0.2127 | 0.1 | 0.2127 | 0.8 |
3 | 0.5147 | 0.5103 | 0.3444 | 0.2 | 0.3450 | 0.5 | 0.3456 | 0.8 |
4 | 0.5142 | 0.5051 | 0.3450 | 0.2 | 0.3462 | 0.5 | 0.3475 | 0.8 |
5 | 0.5142 | 0.5046 | 0.3451 | 0.2 | 0.3464 | 0.5 | 0.3477 | 0.8 |
6 | 0.5142 | 0.5088 | 0.3447 | 0.2 | 0.3454 | 0.5 | 0.3461 | 0.8 |
7 | 0.5142 | 0.5093 | 0.3447 | 0.2 | 0.3453 | 0.5 | 0.3460 | 0.8 |
8 | 0.5142 | 0.5190 | 0.3441 | 0.1 | 0.3441 | 0.1 | 0.3441 | 0.1 |
9 | 0.5142 | 0.5103 | 0.3446 | 0.2 | 0.3451 | 0.5 | 0.3456 | 0.8 |
10 | 0.5142 | 0.5051 | 0.3451 | 0.2 | 0.3463 | 0.5 | 0.3475 | 0.8 |
11 | 0.5142 | 0.5046 | 0.3451 | 0.2 | 0.3464 | 0.5 | 0.3477 | 0.8 |
6.5 CEO banker genetic algorithm validation
Day | Error | Nucleoid-C | Nucleoid-G | Nucleoid-A | Nucleoid-T |
---|---|---|---|---|---|
2 | 3.05E−31 | 0.2048 | 0.3893 | 0.6295 | 0.9268 |
3 | 5.85E−31 | 0.2026 | 0.3861 | 0.6263 | 0.9259 |
4 | 6.78E−32 | 0.2025 | 0.3859 | 0.6262 | 0.9259 |
5 | 1.17E−31 | 0.2029 | 0.3865 | 0.6267 | 0.9260 |
6 | 4.44E−31 | 0.2033 | 0.3870 | 0.6272 | 0.9262 |
7 | 1.29E−31 | 0.2049 | 0.3894 | 0.6296 | 0.9269 |
8 | 3.61E−31 | 0.2031 | 0.3868 | 0.6271 | 0.9261 |
9 | 2.96E−31 | 0.2021 | 0.3852 | 0.6255 | 0.9257 |
10 | 6.90E−31 | 0.2020 | 0.3851 | 0.6254 | 0.9256 |
11 | 1.36E−31 | 0.2023 | 0.3856 | 0.6259 | 0.9258 |
Error genetic | Iteration | Time (ns) | |
---|---|---|---|
Value | 3.13E−31 | 1.00 | 3.17E+05 |
σ | 2.11E−31 | 0.00 | 5.75E+04 |
95% CR | 1.31E−31 | 0.00 | 3.56E+04 |
7 Cryptocurrency evaluation
7.1 Asset banker reinforcement learning validation
Asset | Profit | Maximum profit | Ratio | Win | Loss | Buy | Sell |
---|---|---|---|---|---|---|---|
BITSTAMP | 192,530 | 957,018 | 0.20 | 386 | 277 | 597 | 66 |
BTCE | 177,133 | 749,307 | 0.24 | 355 | 258 | 595 | 68 |
COINBASE | 172,257 | 985,625 | 0.17 | 383 | 279 | 503 | 160 |
KRAKEN | 187,647 | 977,763 | 0.19 | 367 | 258 | 619 | 44 |
Bitcoin | 195,083 | 952,339 | 0.20 | 393 | 270 | 634 | 29 |
Ethereum | 18,626 | 58,916 | 0.32 | 332 | 322 | 385 | 278 |
Ripple | 17 | 101 | 0.17 | 292 | 370 | 662 | 1 |
Total | 943,293 | 4,681,069 | 0.20 | 2508 | 2034 | 3995 | 646 |
Asset | Profit | Maximum profit | Ratio | Win | Loss | Buy | Sell |
---|---|---|---|---|---|---|---|
BITSTAMP | 196,226 | 957,018 | 0.21 | 389 | 274 | 644 | 19 |
BTCE | 180,596 | 749,308 | 0.24 | 371 | 242 | 659 | 4 |
COINBASE | 192,951 | 985,625 | 0.20 | 392 | 270 | 644 | 19 |
KRAKEN | 188,704 | 977,763 | 0.19 | 366 | 259 | 648 | 15 |
Bitcoin | 196,059 | 952,339 | 0.21 | 385 | 278 | 496 | 167 |
Ethereum | 19,446 | 58,916 | 0.33 | 355 | 299 | 175 | 488 |
Ripple | 20 | 101 | 0.20 | 293 | 369 | 663 | 0 |
Total | 974,002 | 4,681,070 | 0.21 | 2551 | 1991 | 3929 | 712 |
Asset | Profit | Maximum profit | Ratio | Win | Loss | Buy | Sell |
---|---|---|---|---|---|---|---|
BITSTAMP | 196,226 | 957,018 | 0.21 | 389 | 274 | 644 | 19 |
BTCE | 191,875 | 749,308 | 0.26 | 373 | 240 | 631 | 32 |
COINBASE | 192,951 | 985,625 | 0.20 | 392 | 270 | 644 | 19 |
KRAKEN | 187,052 | 977,763 | 0.19 | 359 | 266 | 643 | 20 |
Bitcoin | 202,803 | 952,339 | 0.21 | 394 | 269 | 613 | 50 |
Ethereum | 21,476 | 58,916 | 0.36 | 339 | 315 | 432 | 231 |
Ripple | 20 | 101 | 0.20 | 293 | 369 | 663 | 0 |
Total | 992,403 | 4,681,070 | 0.21 | 2539 | 2003 | 4270 | 371 |
7.2 Asset banker deep learning cluster validation
Period | Asset 1 | Asset 2 | Asset 3 | Asset 4 | Asset 5 | Asset 6 | Asset 7 |
---|---|---|---|---|---|---|---|
664 days | It: 1854.67 | It: 945.43 | It: 670.24 | It: 524.43 | It: 436.12 | It: 377.75 | It: 336.71 |
2015–2017 | E: 9.60 | E: 9.51 | E: 9.45 | E: 9.34 | E: 9.24 | E: 8.94 | E: 8.71 |
7.3 Market banker deep learning management cluster validation
Market | Total asset banker | Market banker | I (%) | Maximum asset banker | Maximum market banker | I (%) |
---|---|---|---|---|---|---|
Exchange | 729,567 | 541,559 | − 25.77 | 3,669,714 | 3,731,781 | 1.69 |
Currency | 213,726 | 472,323 | 120.99 | 1,011,356 | 2,050,320 | 102.73 |
Market | Total asset banker | Market banker | I (%) | Maximum asset banker | Maximum market banker | I (%) |
---|---|---|---|---|---|---|
Exchange | 758,477 | 596,973 | − 21.29 | 3,669,714 | 3,403,866 | − 7.24 |
Currency | 215,525 | 547,631 | 154.09 | 1,011,356 | 2,003,275 | 98.08 |
Market | Total asset banker | Market banker | I (%) | Maximum asset banker | Maximum market banker | I (%) |
---|---|---|---|---|---|---|
Exchange | 768,104 | 427,220 | − 44.38 | 3,669,714 | 3,335,495 | − 9.11 |
Currency | 224,299 | 531,675 | 137.04 | 1,011,356 | 2,271,457 | 124.60 |
Period | IBondMarketBanker | wBondMarketBanker−(c) | YBondMarketBanker | ||||||
---|---|---|---|---|---|---|---|---|---|
Bond market banker | |||||||||
664 days 2015–2017 | 0.99 | 0.99 | 0.99 | 0.99 | 0.21 | 0.29 | 0.25 | 0.25 | 0.35 |
Period | IDerivativeMarketBanker | wDerivativeMarketBanker−(c) | YDerivativeMarketBanker | ||||||
---|---|---|---|---|---|---|---|---|---|
Derivative market banker | |||||||||
664 days 2015–2017 | 0.99 | 0.99 | 0.99 | N/A | 0.65 | 0.28 | 0.07 | N/A | 0.29 |
7.4 CEO banker deep learning management cluster validation
Risk β = 0.2 | Risk β = 0.5 | Risk β = 0.8 | Max profit | |||
---|---|---|---|---|---|---|
E | C | E | C | E | C | |
758,183 | 220,418 | 473,864 | 551,044 | 189,546 | 881,670 | 6,181,310 |
Total: 978,600 | Total: 1,024,908 | Total: 1,071,216 |
Risk β = 0.2 | Risk β = 0.5 | Risk β = 0.8 | Max profit | |||
---|---|---|---|---|---|---|
E | C | E | C | E | C | |
835,763 | 255,561 | 522,352 | 638,903 | 208,941 | 1,022,244 | 5,700,274 |
Total: 1,091,324 | Total: 1,161,254 | Total: 1,231,185 |
Risk β = 0.2 | Risk β = 0.5 | Risk β = 0.8 | Max profit | |||
---|---|---|---|---|---|---|
E | C | E | C | E | C | |
598,107 | 248,115 | 373,817 | 620,287 | 149,527 | 992,460 | 5,729,706 |
Total: 846,222 | Total: 994,104 | Total: 1,141,986 |
Period | ICEO-Banker | Risk β = 0.2 | Risk β = 0.5 | Risk β = 0.8 | ||||
---|---|---|---|---|---|---|---|---|
YCEO-Banker | D | YCEO-Banker | D | YCEO-Banker | D | |||
664 days 2015–2017 | 0.3530 | 0.2904 | 0.4422 | 0.2 | 0.4562 | 0.5 | 0.4712 | 0.8 |
7.5 CEO banker genetic algorithm validation
Error genetic | Iteration | Time (ns) | Nucleoid | ||||
---|---|---|---|---|---|---|---|
C | G | A | T | ||||
Value | 6.76E−31 | 1.00 | 1.21E+05 | 0.1849 | 0.3594 | 0.5992 | 0.9177 |
σ | 7.91E−31 | 0.00 | 1.29E+05 | 0.0064 | 0.0098 | 0.0103 | 0.0033 |
95% CR | 6.02E−32 | 0.00 | 9.81E+03 | 0.0005 | 0.0007 | 0.0008 | 0.0002 |