Determining Optimal Trading Rules without Backtesting - Matlab, R project and Python | futures io social day trading

Determining Optimal Trading Rules without Backtesting
 Updated: August 27th, 2014 (03:07 PM) Views / Replies: 623 / 3 Created: August 14th, 2014 (01:27 PM) by Big Mike Attachments: 1

 Welcome to futures io.

Determining Optimal Trading Rules without Backtesting

Platform: My own custom solution
Favorite Futures: E-mini ES S&P 500

Posts: 46,336 since Jun 2009

Determining Optimal Trading Rules without Backtesting

Source: [1408.1159] Determining Optimal Trading Rules without Backtesting

Peter P. Carr, Marcos Lopez de Prado

(Submitted on 6 Aug 2014)

Calibrating a trading rule using a historical simulation (also called backtest) contributes to backtest overfitting, which in turn leads to underperformance. In this paper we propose a procedure for determining the optimal trading rule (OTR) without running alternative model configurations through a backtest engine. We present empirical evidence of the existence of such optimal solutions for the case of prices following a discrete Ornstein-Uhlenbeck process, and show how they can be computed numerically. Although we do not derive a closed-form solution for the calculation of OTRs, we conjecture its existence on the basis of the empirical evidence presented.

PDF attached.

Mike

Attached Thumbnails

 The following 5 users say Thank You to Big Mike for this post:

 August 14th, 2014, 01:27 PM #2 (permalink) Quick Summary Quick Summary Post Quick Summary is created and edited by users like you... Add FAQ's, Links and other Relevant Information by clicking the edit button in the lower right hand corner of this message.

Platform: My own custom solution
Favorite Futures: E-mini ES S&P 500

Posts: 46,336 since Jun 2009

Code
 ```#!/usr/bin/env python # Profit-taking and stop-loss simulations # On 20131003 by MLdP import numpy as np from random import gauss from itertools import product #---------------------------------------------------------------------------------------- def main(): rPT=rSLm=np.linspace(0,10,21) count=0 for prod_ in product([10,5,0,-5,-10],[5,10,25,50,100]): count+=1 coeffs={'forecast':prod_[0],'hl':prod_[1],'sigma':1} output=batch(coeffs,nIter=1e5,maxHP=100,rPT=rPT,rSLm=rSLm) return output #---------------------------------------------------------------------------------------- def batch(coeffs,nIter=1e5,maxHP=100,rPT=np.linspace(0,10,21), \ rSLm=np.linspace(0,10,21),seed=0): phi,output1=2**(-1./coeffs['hl']),[] for comb_ in product(rPT,rSLm): output2=[] for iter_ in range(int(nIter)): p,hp,count=seed,0,0 while True: p=(1-phi)*coeffs['forecast']+phi*p+coeffs['sigma']*gauss(0,1) cP=p-seed;hp+=1 if cP>comb_[0] or cP<-comb_[1] or hp>maxHP: output2.append(cP) break mean,std=np.mean(output2),np.std(output2) print comb_[0],comb_[1],mean,std,mean/std output1.append((comb_[0],comb_[1],mean,std,mean/std)) return output1```
Mike

 The following 2 users say Thank You to Big Mike for this post:

 August 27th, 2014, 03:07 PM #4 (permalink) Vendor: sentimentrader.com  Tulsa, OK   Futures Experience: Advanced Platform: Tradestation, TOS, Python Broker/Data: IQFeed, Tradestation, TOS Favorite Futures: ES, SPY, Options     Posts: 201 since Jan 2011 Thanks: 339 given, 238 received Nice find...i'm a fan of Marcos López de Prado's work. I've added this to my reading list.

 futures io > Determining Optimal Trading Rules without Backtesting

Upcoming Webinars and Events (4:30PM ET unless noted)

Elite only

Digging into the Details of iSystems w/Stage 5 & iSystems

Jun 5

 Similar Threads Thread Thread Starter Forum Replies Last Post Anagami The Elite Circle 4 January 25th, 2015 03:15 PM Adamus Tech Support 4 October 21st, 2013 05:22 AM JohnPS Traders Hideout 14 December 31st, 2010 10:16 PM

All times are GMT -4. The time now is 06:21 AM.

 Copyright © 2018 by futures io, s.a., Av Ricardo J. Alfaro, Century Tower, Panama, +507 833-9432, info@futures.io All information is for educational use only and is not investment advice.There is a substantial risk of loss in trading commodity futures, stocks, options and foreign exchange products. Past performance is not indicative of future results.
no new posts
Page generated 2018-05-26 in 0.08 seconds with 20 queries on phoenix via your IP 54.224.108.85