12.1) What is 'Walk Forward Analysis' and how does it improve Trading System Optimizations

Walk Forward Analysis (WFA) provides many advantages over a standard optimization process and helps algorithmic traders produce more effective trading systems. Also called Walk Forward Optimization (WFO), this backtesting method overcomes a number of major issues inherent in the standard approach. This episode shows how Walk Forward Analysis provides a solution.
Brought to you by Darwinex: UK FCA Regulated Broker, Asset Manager & Trader Exchange where Traders can legally attract Investor Capital and charge Performance Fees:
www.darwinex.c...
OTHER PARTS TO THIS EPISODE:
Easy access to all parts of this episode:
Part 1: • 12.1) What is 'Walk Fo... (This part)
Part 2: • 12.2) Using 'Walk Forw...
VIEW THE WHOLE 'BACKTESTING & OPTIMIZATION' SERIES IN ONE PLACE:
• Algorithmic Backtestin...
-----------------------
IMPORTANT REQUEST: Please please please.. if you find this content useful, please do consider liking and sharing it on TH-cam, Twitter, Facebook, LinkedIn, and whatever other social networks you have circles in.
Darwinex relies almost exclusively on organic growth, primarily through recommendation via informative content.
TH-cam’s algorithms measure the quality of Darwinex content on the basis of:
- Reach
- Engagement
- and several other related variables
With seemingly small actions such as:
- Clicking the Like button
- Clicking the Subscribe button
- Clicking the Share button (on TH-cam) and distributing our content
- etc
… YOU inform TH-cam’s algorithms of your sentiment towards Darwinex, thereby directly helping Darwinex MASSIVELY in achieving organic growth.
Thank you very much for your kind consideration!
-----------------------
Risk disclosure:
www.darwinex.c...
** Fancy joining a vibrant community of algorithmic traders, quants and data scientists focused on financial hacking? Join the Darwinex Collective Slack Workspace:
join.slack.com...
#WalkForwardAnalysis, #WalkForwardOptimization, #AlgoTrading, #MultiStageOptimization, #RobertPardo, #Backtesting, #Darwinex, #BobPardo, #MT4, #MT5, #MetaTrader, #WFA, #WFO

[@leonjbr]

Clear and useful.

[@martyntinsley]

As always, thanks for the feedback Leon

[@MrA1wizard]

This great work. Thank you for this.

[@caioagrizzi]

impossible to be clearer

[@bsbrosentertainment8637]

Having to optimize 4 parameters, (if I understood) it is better to do two optimizations​ with two parameters at a time.
Parameters: A (A1-A10) B(B1-B10) C(C1-C10) D(D1-D10)
Therefore,​ first optimization A and B, and second​ ​ C and D.
Example first scan best result A3 B9, the second scan in order to optimize C and D will be done with the parameters of first scan A3 and B9.
Is it correct? Of course doing a walk forward optimization TF5m 4mounth+1 I'll repeat it for 5 times (forward 1 month per time) as your webinar WFO.
Is it correct?

[@specialagentslowhand]

Great content. What does it mean if the walk forward (out-sample) performance is better than optimized (in-sample) performance? Similarly, what if each phase seems to improve? I would expect performance to degrade over time. Thank you for this!

[@ulziibaatar2369]

What is best period interval for novice algo traders?

[@martyntinsley]

Hi Ulzil. Can I recommend that you watch the next episode (Episode 13) where I hopefully answer your question in quite a lot of detail. You can find it here: th-cam.com/video/sjm60E3IXms/w-d-xo.html
Hope this helps

[@diegosoto6516]

Great stuff...u Say un one of tour videos that one shouldn't optimizw more than at most 3 parameters...but what happens ir i'm teeting a strategy which has Lot of parameters...more than 10...moreover what happens i'm the scenario un which i'm looking for the Best combinación of múltiple strategies...with fixed parameters...

[@nehemaialord2653]

This would be hard to do on the daily timeframe because of the low historical data. I trade on the daily timeframe because it’s the best timeframe

[@muammaranwar6971]

Can i do it in metastock? Has metastock's system tester included Walk-Forward Analysis in its backtesting and optimization?

[@lukexu4845]

Wouldn't it also be viable to have a long optimization phase and having a system which is adjusted all market conditions? Suffering lower returns short term seems like a good trade-off for a system that can perform well regardless of market conditions. Curious is all. Thanks for the vids!

[@TradeLikeAMachine]

Hi Luke. I think I understand what you mean. So during the longer opt period, your system would have an ability to adapt real-time based on what the market is doing, right? If so then yes, absolutely. This is a very viable approach. But if your system doesn't do this , then WFA is a great alternative to stay in tune with conditions. Hope this helps. Cheers, Martyn

[@marcovalentinoalvarado3290]

In the other hand... I think the opposite, I strongly believe, that any model specifically designed for a market condition (I.E ranging market) that trades on that specific condition is healthier for the equity curve rather than having a model that trades at any market condition, that way you can design another model for example, designed for momentum trading, and *bring up the concept of diversification up a little bit better...* I don't remember where I've heard that trying to design a model with great performance in all market conditions is just innocent and such model should not be attempted to achieve. Speaking of... Martyn Tinsley here have made a few videos about how important "Diversification" is! Check 'em out!

[@hugh2200]

Where can I get the excel walk-forward file?