Adaptrade Builder
Pravidlá fóra
Nezabudnite, prosím, že svojou prítomnosťou a diskutovaním na tomto fóre vyjadrujete svoj súhlas s vždy aktuálnymi Podmienkami používania tohto fóra. Predovšetkým prosím dbajte na slušnosť komunikácie a rešpektovanie sa navzájom. Celé Podmienky používania tohto fóra si môžte prečítať tu.
Nezabudnite, prosím, že svojou prítomnosťou a diskutovaním na tomto fóre vyjadrujete svoj súhlas s vždy aktuálnymi Podmienkami používania tohto fóra. Predovšetkým prosím dbajte na slušnosť komunikácie a rešpektovanie sa navzájom. Celé Podmienky používania tohto fóra si môžte prečítať tu.
Clever Algorithms: Nature-Inspired Programming Recipes
45 Algorithm Descriptions
http://www.cleveralgorithms.com/
The book includes an introduction to artificial intelligence and related fields as well as advanced topics like algorithm testing and visualization.
The 45 algorithms are grouped into chapters, as follows:
Stochastic Algorithms: Random Search, Adaptive Random Search, Stochastic Hill Climbing, Iterated Local Search, Guided Local Search, Variable Neighborhood Search, GRASP, Scatter Search, Tabu Search and Reactive Tabu Search.
Evolutionary Algorithms: Genetic Algorithm, Genetic Programming, Evolution Strategies, Differential Evolution, Evolutionary Programming, Grammatical Evolution, Gene Expression Programming, Learning Classifier System, NSGA and SPEA.
Physical Algorithms: Simulated Annealing, Extremal Optimization, Harmony Search, Cultural Algorithm and the Memetic Algorithm
Probabilistic Algorithms: PIBL, UMDA, Compact Genetic Algorithm, Bayesian Optimization Algorithm and the Cross-Entropy Method.
Swarm Algorithms: Particle Swarm Optimization, Ant System, Ant Colony Optimization, Bees Algorithm and the Bacterial Foraging Optimization Algorithm.
Immune Algorithms: Clonal Selection Algorithm, Negative Selection Algorithm, Artificial Immune Recognition System, Immune Network Algorithm and the Dendritic Cell Algorithm.
Neural Algorithms: Perceptron, Back-Propagation, Hopfield Network, Learning Vector Quantization and the Self-Organizing Map.
All algorithm descriptions include a working implementation of the algorithm in Ruby. The standalone ruby files for each algorithm are also included in your download.
Read Online
http://www.cleveralgorithms.com/nature- ... index.html
http://www.cleveralgorithms.com/
The book includes an introduction to artificial intelligence and related fields as well as advanced topics like algorithm testing and visualization.
The 45 algorithms are grouped into chapters, as follows:
Stochastic Algorithms: Random Search, Adaptive Random Search, Stochastic Hill Climbing, Iterated Local Search, Guided Local Search, Variable Neighborhood Search, GRASP, Scatter Search, Tabu Search and Reactive Tabu Search.
Evolutionary Algorithms: Genetic Algorithm, Genetic Programming, Evolution Strategies, Differential Evolution, Evolutionary Programming, Grammatical Evolution, Gene Expression Programming, Learning Classifier System, NSGA and SPEA.
Physical Algorithms: Simulated Annealing, Extremal Optimization, Harmony Search, Cultural Algorithm and the Memetic Algorithm
Probabilistic Algorithms: PIBL, UMDA, Compact Genetic Algorithm, Bayesian Optimization Algorithm and the Cross-Entropy Method.
Swarm Algorithms: Particle Swarm Optimization, Ant System, Ant Colony Optimization, Bees Algorithm and the Bacterial Foraging Optimization Algorithm.
Immune Algorithms: Clonal Selection Algorithm, Negative Selection Algorithm, Artificial Immune Recognition System, Immune Network Algorithm and the Dendritic Cell Algorithm.
Neural Algorithms: Perceptron, Back-Propagation, Hopfield Network, Learning Vector Quantization and the Self-Organizing Map.
All algorithm descriptions include a working implementation of the algorithm in Ruby. The standalone ruby files for each algorithm are also included in your download.
Read Online
http://www.cleveralgorithms.com/nature- ... index.html
"Have you taken a loss? Forget it quick. If you have taken a profit, forget it quicker. Don’t let ego and greed inhibit clear thinking and hard work. It is profitable to study your mistakes. "
FREE QUANTITATIVE FINANCE RESOURCES
"Have you taken a loss? Forget it quick. If you have taken a profit, forget it quicker. Don’t let ego and greed inhibit clear thinking and hard work. It is profitable to study your mistakes. "
Quant at Risk
"Have you taken a loss? Forget it quick. If you have taken a profit, forget it quicker. Don’t let ego and greed inhibit clear thinking and hard work. It is profitable to study your mistakes. "
Pseudo-Mathematics and Financial Charlatanism
- Prílohy
-
- Pseudo-Mathematics and Financial Charlatanism.pdf
- Pseudo-Mathematics and Financial Charlatanism
- (2.86 MiB) 580 stiahnutí
"Have you taken a loss? Forget it quick. If you have taken a profit, forget it quicker. Don’t let ego and greed inhibit clear thinking and hard work. It is profitable to study your mistakes. "
Know Your System!
Know Your System! – Turning Data Mining from Bias to Benefit through
System Parameter Permutation
http://papers.ssrn.com/sol3/papers.cfm? ... id=2423187
System Parameter Permutation
http://papers.ssrn.com/sol3/papers.cfm? ... id=2423187
- Prílohy
-
- Know Your System!.pdf
- Turning Data Mining from Bias to Benefit through
System Parameter Permutation - (1.39 MiB) 311 stiahnutí
"Have you taken a loss? Forget it quick. If you have taken a profit, forget it quicker. Don’t let ego and greed inhibit clear thinking and hard work. It is profitable to study your mistakes. "
-
- Platinum Member ***
- Príspevky: 968
- Dátum registrácie: Ut 11 11, 2014 4:07 pm
- Has thanked: 1 time
- Been thanked: 7 times
-
- Platinum Member ***
- Príspevky: 968
- Dátum registrácie: Ut 11 11, 2014 4:07 pm
- Has thanked: 1 time
- Been thanked: 7 times
Re: Adaptrade Builder
fuha 3, teda +3 teda 4, to znie dost podozrivo ale trebars... nerozumiem 0.61 0.36 a 0.33 teda prvym dvoj aj ano ale ten treti by mal byt (IMHO) 0.25 ... ale trebars musim trochu vytriezviet inak statny novy rok ..jaroslav80 napísal:Kolega - a co keby si vyriesil tu penalizaciu takto:
Ziskovost prvej premennej by bola X% a zaujimali by ta uz len take dalsie premenne, ktore by navysovali ziskovost aspon o 0,3*X%. Cize ak by si nasiel tri take premenne, vychadzal by ti trebars zisk X% + 0,61*X% + 0,36*X% + 0,33*X%. A take ze +0,22*X%, +0,07*X% by si ignoroval a nekomplikoval nimi system.
ja to zatial robim ze 2. podmienka 1/2 (50%) potom 1/3 (+33%) ....n .. (+1/n %)
... takto to mam zatial implementovane v mojom programe ale trebars dojdem k inej pravde
Re: Adaptrade Builder
aaaaaaa vsak ja sa vynajdem a ked budem velky a bohaty vsetkych vas pozvemMartinPillar napísal:
Re: Role of Backtesting in Trading System Development
Ahoj,radvan napísal: pozri si hypothesis testing a zaklady statistiky ... na toto sa vacsinou pouzyva t-statistic parameter ... ak je t-statistic nad 2kou tak na 95% to neni nahoda ale najaky pattern ...
samozrejme testovanie hypotez v tradingu prinasa vlastne problemy ... a to ze ked dostatocne dlho mucis data, tak najdes statisticky vyznamne patterny aj nahodou ... takze trosku to pomoze pouzivat t-statistic, ale ako zo vsetkym, treba opatrne ...
pocuj pozeram t-statistic, ak tomu vzorcu dobre rozumiem vlastne iba vyhodnocuje aka je variacia v datach a aky priemer (profitu na jeden obchod (???)) dosiahla strategia, no ale co ak mam strategiu na x trhoch a trebars tie trhy nie su zrovna pribuzdne a teda mix tych dat bude mat velku variabilitu co vlastne horsie hodnoti vysledky strategie co sa mi nepaci
ako by si to riesil ? alebo to nevadi ?
diky
-
- VETERAN MEMBER *****
- Príspevky: 4057
- Dátum registrácie: Št 24 03, 2011 5:19 pm
- Has thanked: 54 times
- Been thanked: 69 times
Re: Adaptrade Builder
Hovorime o tom istom, len inymi slovami, inym vzorcom.kolega napísal:
ja to zatial robim ze 2. podmienka 1/2 (50%) potom 1/3 (+33%) ....n .. (+1/n %)
Pridanim n-tej podmienky zvysit ziskovot strategie o 1/n% je to iste, ako oznacit prvu podmienku "X" a povedat, ze akukolvek dalsiu pridas jedine ak ziskovost zvysi aspon o 0,5*X.
Cize aj stvrta premenna musi ziskovost zvysit aspon o 50% prvej, aj patnasta premenna musi zvysit ziskovot aspon o 50% prvej.
Ja by som navrhoval hranicu 50% znizit na 30% ... skomplikovat si system by za ten navyseny zisk snad este stalo.
Re: Adaptrade Builder
No ok, tak prerobil som to aby bola fitnes definovana iba T-statistics,
Nechal som to bezat iba 2 generacie
najlepsia strategia ma hodnotu 4, je to iba jedna podmienka ktora prepusta filtrom 30% dat, podmienka je velmi jednoducha trendova. je zvlastne ze tam je aj strategia ktora ma vacsiu ziskovost ale kedze ma trochu menej obchodov tak ma nizsiu t-statistics,
Musim to vyskusat este na viacej dat, zatial to bolo iba na mesacnych datach kovov. (a mesacnych dat je vzdy malo).
Tiez tam mm zatial iba 8 podmienok na vyber, planujem tak do 100
Nechal som to bezat iba 2 generacie
najlepsia strategia ma hodnotu 4, je to iba jedna podmienka ktora prepusta filtrom 30% dat, podmienka je velmi jednoducha trendova. je zvlastne ze tam je aj strategia ktora ma vacsiu ziskovost ale kedze ma trochu menej obchodov tak ma nizsiu t-statistics,
Musim to vyskusat este na viacej dat, zatial to bolo iba na mesacnych datach kovov. (a mesacnych dat je vzdy malo).
Tiez tam mm zatial iba 8 podmienok na vyber, planujem tak do 100
Re: Adaptrade Builder
zdravim vas
rad by som sa opytal ci viete o nejakom rieseni (mozno podobne ako AB) ktore by svoj softver predavali ako servis, teda cisto online ? (bez instalacie softu, beziace na stranke/serveri...)
Diky.
rad by som sa opytal ci viete o nejakom rieseni (mozno podobne ako AB) ktore by svoj softver predavali ako servis, teda cisto online ? (bez instalacie softu, beziace na stranke/serveri...)
Diky.