Activity
Mon
Wed
Fri
Sun
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
What is this?
Less
More
5 contributions to QuantConnect Mastery
Case Study: QuantConnect Momentum Pullback Strategy (13.8% CAGR, -20,7% DD)
Buying two-day flushes in strong large-cap uptrends returned 13.8% a year at a 20.7% drawdown against the S&P 500's 10.9% at 55.0%, and it made 4.3% through the financial crisis while the S&P 500 lost 54.1%. The full write-up, including how it was built and what failed, is on the case study page
Case Study: QuantConnect Momentum Pullback Strategy (13.8% CAGR, -20,7% DD)
1 like • 2d
@Tim Sergeev that's an excellent idea for creating a video on how to improve strategy. Although a written document/manual would go a long way as well because it will serve as a nice guideline
1 like • 2d
@Tim Sergeev yes, I would love to do a contest and see how we can improve our strategy, and then compare our results. Great idea. This is exactly what QuantConnect experience should be about: taking existing strategies from other sources and improving upon them, assuming there was a small edge to the strategy to begin with in the initial testing.
🚀 New Video: QuantConnect Backtesting Tutorial: How to Backtest Any Strategy with Claude Code
In this video I walk through the whole process from scratch, step by step. I open a QuantConnect account and a Claude account, connect Claude to QuantConnect through the MCP, open Claude Code, and then use it to backtest a strategy on QuantConnect. At the end I go through the backtest results so you know how to read them and what the numbers actually mean. ⚠️ By the way, to use QuantConnect MCP you need to pay for Assistant Compute Node on QuantConnect whereas if you use Strategy Research Lab (which is provided to members of this community) then you don't have to pay for it and still run all backtests. Thats 24$/month savings.
1 like • 2d
Also from what I understand, traditionally MCP also uses a lot more tokens. But for those who don't want to mess around with learning VS Code or want to have the ability to do this from anywhere on a cloud and not from their home computer only, then it's a reasonable alternative.
Backtesting node
Hello everybody, Just wanted to know what node subscription everybody has for their backtesting with QuantConnect. I'm currently subscribed to two nodes on the. B2-8. Anyone else have something different that is generating better performance, or is everybody relying on the free node?
0 likes • 2d
@Tim Sergeev Yes, I use my original kit. Plus, Claude integrated a lot of your kit elements into it for items that it didn't initially have. Also, a lot of the course material that you recently provided has been used as a source to ensure that my kit cover all angles in research and strategy analysis. So i feel like i have a pretty robust kit at the moment, my Claude.md file is close to 500 lines and it references to couple of supporting MD files and an addition 20 custom skills as it goes through the strategy phases. So once I feed it strategy details, it systematically goes through it and does its testing, and ensures all the necessary details are there in case I missed something. The problem is that, in the planning stage, it keeps asking me so many questions because it's designed to cover all the angles. I feel like I'm going back and forth for a long time before it starts to get to backtesting. I guess considering everything it's trying to cover, its no wonder. I just wanted to see if it had anything to do with the claude model im using so I didn't have to spend so much time reading its responses which at times I find confusing After that, its smooth sailing on each phase of testing as it guides itself basically to ensure all angles are covered. Perhaps with experience, I'll get better at this. It's just a matter of time
0 likes • 2d
Also, im willing to share my kit if anyone is interested. It comes with a 40+ page guide ... Although it's very rough and customized to what I did and is not as easy to follow as Tim's course ... anyhow, DM me if interested
"Master QuantConect with Claude" course is here 🎉
I have spent countless hours writing this, and it is finally live! Fifteen modules that take you from an idea to a strategy running on your own money. It comes with the Strategy Research Lab, the tool I use myself. You describe what you want in plain English and it writes the strategy, runs the backtest and reads the result back to you. You never type a command and you never write code. There are also the case studies, where I open up my own research, what I've tested, what the numbers came back as, which ideas held up and which ones I threw out. And as a cherry on the cake I share the full source code of all strategies. Thank you for your help and support!
"Master QuantConect with Claude" course is here 🎉
1 like • 3d
Very in-depth course and thoroughly thought out, covering multiple angles. I've done a few backtests myself prior to this course, but I haven't considered quite a lot of aspects during my backtesting clearly. I tend to let Claude guide me quite a bit instead of me steering it in the right direction and working together instead. I think with the amount of information this course has provided, the user can really engage more with Claude. But at the end of the day, the real trick is to actually put this all into practice so it becomes second nature. Hopefully, by the end of the year, we can be on a similar page that Tim is on.
Trading vs. Passive Investing: What are realistic return expectations?
Hey everyone! As I build out my understanding of strategy design and risk management, I keep coming back to a fundamental question: What is a realistic expectation for annual returns, and when is active trading actually worth the effort compared to passive investing? We know that long-term passive indexing (like holding the S&P 500) historically yields around 8%–10% per year with virtually zero daily effort. For those of you running systematic or active trading strategies: 1. Realistic Benchmarks: What annual return (or Sharpe Ratio) do you target to justify the extra time, market risk, and transaction costs of active trading? 2. Trading vs. Investing: In your experience, at what point does active trading truly outpace a solid "buy and hold" passive portfolio once you account for drawdown and effort? Would love to hear your perspectives on setting grounded expectations! 🚀
1 like • 9d
Wow, 40% return. That's pretty impressive. I'm surprised more companies wouldn't jump on this bandwagon. I wonder what kind of platform they use, if it's QuantConnect as well or their own proprietary platform with a team of analysts and programmers doing all the backtesting work.
1 like • 9d
@Tim Sergeev yeah, we basically have the same tools, yet don't have the overhead they do. So even though they produced 40% annual returns after commissions, they still had to pay an army of PhD employees eating into their profits. 😄
1-5 of 5
Zoran Jovanovic
2
4 points to level up
@zoran-jovanovic-2222
I love exploring new ideas in QuantConnect, moving on from TradingView, which I found very limiting in certain ways

Active 3h ago
Joined Sep 27, 2026
Powered by