Neural Net Side Project Makes $3500/mo Trading Stocks
indiehackers.com
indiehackers.com
[1] Running cat on a csv file would usually just print a list of numbers, yes? Instead he gets ascii art with months on the vertical axis, making it seem like time going back and forth, and some random commentary in the right margin. I dunno but something about it screams "mockup". As does the minimalist, ultra-stylish AWS window.
Edit: also, if it were me who got incredible returns from trading at high speed on indian markets using only machine learning on historical data, I would definitely keep quiet about it. Just sayin'...
The general vagueness of the post is a much much much stronger reason to be skeptical, imo.
Anyway, like I said, I'm not trying to say the post is factual. Just trying to point out that the fact that he cat'ed a CSV and got a plot isn't that big a deal (and shouldn't really be an indication of fraud), in a world where so many of us customize our working environments.
It's possible to generate a highly profitable and successful trading system but it's the expected probability factoring in the worst case downside scenarios that really matters.
After all, you could win 9 out of 10 times but that 1 time is where you blow up.
Right now, I'm putting my wall street hat on and calling this bullshit. A naive software developer will not be able to see the potential pitfall of holy grail systems-they do not exist.
I also question if it's really HFT, the bar is really high to get low latency connection but he's only making 3.5k/month...it just doesn't make sense.
And why would you publish your system and say oops I can't tell you anything about it?
In the article he discussed exactly this happening.
> I also question if it's really HFT, the bar is really high to get low latency connection but he's only making 3.5k/month...it just doesn't make sense.
Again, in the article he states that he abandoned his HFT approach.
Most of these negative comments seem to come from people involved in trading who didn't read the full article but are extrapolating based on their knowledge of finance.
As I was invited to share my story on Indie Hackers, my goal was to provide as much insights into the project, without blowing up the advantage it gives me over a very niche market (NSE). I have absolutely no intention to 'advertise my freelancer business' or 'sell my tech', as someone mentioned. My goal was strictly to send an encouragement message to people thinking of/building something similar, by sharing as much as I can of my project. Faking stories online would be the last thing on my agenda and I find it somehow amusing that some people believe that.
PS: Having to cat a lot of text + csv files while developing this, it was much easier to alias my cat function to use csvtool on csv files and it's regular implementation on other files
PS2: The 'minimalist, ultra-stylish AWS window' is a quick app I cranked in a few hours to see the status of my instances. Not sure what's suspicious here. The window or the the fact that it's stylish?
https://www.quantopian.com/open
Easy $5k if it does what you claim and would settle the dispute. You can just feed them trades w/o revealing the actual algo.
Really? You made a crazy claim with no details at all.
Here's my assumptions on this thing:
1. Your algorithmic strategy is only performed on a small selection of stocks, that you have semi-randomly picked, aka not a part of your system.
2. These stocks have had a crazy run.
3. When the NSE had troubles in Nov. and Dec. your conservative stop losses triggered and you stayed out of the market.
4. Your decision on when to re-enter the market was a personal decision, not a part of your system.
5. You have given this thing more money to invest with than we are being led to believe.
Which ones did I miss on?
I gotta be honest, it really does seem like a nice little way to plug you business but I don't believe you're lying. I think you're overstating its performance by leaving out details and were lucky to get that performance in the first place.
Whether you are lying or not does not really matter, after all you're just a regular guy trying to get ahead like the rest of us. And the startup royalty keeps telling us to bend the rules. What I'm criticising is IndieHacker's lack of due diligence to screen for charlatans. I'm assuming you didn't show them any further proof than what's in the article?
I also think most of the stories on indie hacker are bull and it's just people growth hacking or something to get free publicity.
"The claims made in this interview are extremely suspect, it just not make sense. Absolutely no relevant details are included. The developer claims he was able to built an AI trading strategy that is profitable 95% of the time. No technical details about the strategy or platform for trading is provided. A few trading buzzwords thrown in a few places. The rest of the interview is platitudes and inspirational hacker talk
I think IndieHackers needs to investigate the claims and be provided proof, otherwise this appears to be a fake project for the developer's own publicity. If IndieHackers are fine with that, I will stop visiting as I cannot trust that the content is not just shallow, exaggerated claims to raise peoples profiles."
After expressing my concerns directly to IndieHackers, the interview was changed in multiple places to flesh out a number of the spurious claims which I had criticised.
Without further details or some proof from the developer, this piece stinks. Taking into account the rest of the interview which contains stereotypical inspirational hacker talk, the whole thing feels like a badly done promotional bit for SV style status.
If I am wrong, I will apologise and the developer is going to be a multimillionaire very, very quickly. Until there is more details, I am going to be totally sceptical of IndieHacker interviews going forward. Which is a shame as I think IndieHackers is a great site. How can I trust that the other submissions are not baseless, PR pieces?
But hey, maybe this guy really cracked the market, and a Nobel prize and billions of USDs are on the way...
I think you guys are both creating a false dichotomy between "genius who cracked the market" and "liar who is fabricating data", when there is plenty of room in between, e.g. "someone who made a few lucky trades in a bull market over a short period of time," which would describe probably the vast majority of "winners" in the stock market.
It's the equivalent of asserting that everyone who plays a slot machine must break even, when in reality some people win and some people lose.
edit: I rang the bloody alarm bells about this submission with you. I hope I am wrong, but it looks like you have been had.
Addition #1: "For proprietary reasons I will abstain from publicly discussing a lot of details about the technical implementation. Although I get many requests to open-source the project, I believe that disclosing deep details of the models or prediction approach would hurt the advantages that this solutions has over the other existing bots. However, for anyone willing to learn more about that, I would be more than happy to discuss in private, to some extent."
Addition #2: "...worked around 95% of the time. Now this is not by any means a reliable metric, and there are many factors that affect it. The bot has not been tested enough to guarantee that this isn't just a fluke (it might as well be). Large investment management companies would do anything to achieve those statistics, and I'm sure I won't keep up that amount of success in upcoming trades. The success so far was also greatly impacted by the favorable market conditions, chosen stocks, and the fact that the bot was running intermittently."
Addition #3: "For trading I recommend Kite, mainly for their stable Connect APIs and the low bandwidth. Their limitation is 3 requests per second, and this was more than enough for my new strategy. Getting solid historical financial data isn't cheap, and with so many people hitting the providers to scrape and download data, I don't blame them for limiting the offered information. Intrinio is a good provider for real-time stock quotes at very inexpensive prices. However, getting access to more in-depth data would always yield better results."
Your main claim was that the bot cannot achieve 95% trade success trade constantly, which I undoubtedly agreed to and added more details on this claim.
The edit also provided more details about the platforms that I used along the way, as this detail was overlooked in the initial version of the interview.
I find your claims unfounded and harassing.
I am not the only one who is extremely sceptical about your claims.
Articles like this where proper due diligence verifying the authenticity of the poster isn't in place raises strong questions about how reliable and factual IndieHacker is.
I really feel like they fucked up by posting this article. The other article seemed alright but now I ask the same questions.
It seems like they saw the original trendy tweet where he mentioned it and didn't verify anything.
If he had a strategy this good, he would've quit freelancing and be a multimillionaire by now.
The only reason I'm not 100% convinced this is fraud is that it's on the Indian market. I don't know the level of sophistication there, so it might still be possible for an independent trader to exploit winning strategies.
How many hundreds of engineers tried the same thing and won't get an article on the front page of HN because no one wants to read about mediocre performance? I don't want to sound too skeptical, quantitative HFT is absolutely the future, but if enough people try something that's effectively gambling, some of them are bound to succeed, and those people will get dramatically disproportionate exposure.
EDIT: I do still like this post and the project, the infrastructure is great and it offers insight into something I'm sure many people are curious about.
And you bet your ass if I tried and succeeded I'm not going to come here and brag about it, risking whatever ephemeral edge I had. If I did this, I would do it for dollars, not karma points.
And another one by Indiehackers founder csallen after it already hit the front page: http://i.imgur.com/rxWtsWJ.jpg
Also you ignored the first picture which clearly shows your account.
e.g:
Can we tweet a link to our own submission? Can we add a link to the end of a blog post (that we submitted ourselves) with a link to the submission, saying: "Discuss on HackerNews"
How are you determining true alpha? We're in a bull market. Don't mean to sound harsh but this could be blind luck.
I did not read anything about backtesting. Have you done that? If so, I take it back :)
We do not have techniques that account properly for any of these things.
You may as well draw lines on charts and sell that advice, you'd probably get as good a hearing in any Investment Bank in the world !
oh....
wait...
However, in this case, the fact that no backtest or any sort of risk/reward ratios were published suggests high level of skepticism.
tl;dr: past prices can't predict future prices.
Further, accurate back testing is very difficult for lots of reasons, the most obvious being your own actions aren't reflected.
Most algo firms use historical data to develop a hypothesis & then many different ways to validate that hypothesis. Test trading being the one with the most weight.
A friend had a technique that worked very well on the NASDAQ 100 with roughly those BT criteria. One problem was overlooked: The NASDAQ 100 changes over that time. So you aren't necessarily investing in the same securities in year 6 as you were in year 5, even though you're investing in the same "top 100". IOW, backtesting in this particular case had future knowledge that wasn't easy to see.
When he started (paper) trading in the real NASDAQ 100, the returns were negative. In that he was lucky: They could have been positive for some time, until the constituent stocks changed.
When you trade in a live market, your actions cause responses. When backtesting your actions get no responses.
This is almost certainly a fluke, if it's true at all. There aren't any valuable lessons here and such a story merits a high degree of skepticism. Algorithms which can successfully return 95% profits consistently are not wasted on freelance developers.
I usually love Indie Hackers, but including this story really devalues the brand.
I also disagree that there aren't any valuable or inspiring lessons for indie hackers here. In fact, I enumerated some of them as asides in the interview itself, none of which would apply to your hypothetical trip to Vegas.
You and others are hyper-focused on the irrelevant question of whether or not Sebastian's attempt to build an unparalleled money-making machine has succeeded (answer: obviously not), and ignoring the actual point of the interview. It's the equivalent of the guy who read the SubmitHub interview a few months back, ignored all the lessons within, and instead attempted to create an exact clone of the SubmitHub product.
What proof do you have of his claims?
If this turns out to be a dodgy submission for self promotion it is mildly embarrassing for IndieHackers if they admit error in this instance.
If it turns out you have seen no solid proof for these claims and amidst the heavy skepticism express by multiple people in this thread you do not investigate and demand proof, than that calls into question the rest of IndieHackers
What proof do you have of his claims?
What extraordinary claim is being made that requires proof?
Wrong.
"1. How did someone outside the financial world get access to an exchange that would allow this" "First bit of proof I think you should get. 1. Agreement with exchange" "1. I was not even referring to "top" exchanges. even just a single exchange. ask him which one he uses"
>You claimed it was impossible for him to find data sources,
Wrong.
"2. He states that he trained the model on financial data. This data is Extremely expensive. If he is using public data like Yahoo Finance, the level of detail that is provided is so low that it is incredibly unlikely any automated strategy could work off it" "[provide] 3. Data sources for AI training" "2. It is very unlikely a succesfull strategy could be based on this [public data]
> What extraordinary claim is being made that requires proof?
The claim that someone with 5 months of financial self learning has created an AI strategy that makes a profit 95% of the time. That is an extraordinary claim.
I have asked him elsewhere in the thread and still have not had a response.
Post historical and current positions, open and closed.
I've responded to this many times now, and you've ignored me, which is why I don't believe you actually want an answer, so this will be the last time I respond:
Sebastian has not claimed that his strategy will work 95% of the time. That would be crazy. He hasn't even claimed that it has worked 95% of the time –- he specifically stated that if he hadn't manually intervened, it would have lost all his money.
He merely reported that over a limited window of time (5 months) with a limited number of trades (non-HFT) in a bull market, 95% of those trades were profitable. If you break down the math correctly (which you did incorrectly in our Twitter convo), winning 19 out of 20 coin tosses = 1 in 52k. That has surely been done many millions of times, assuming hundreds of millions of trades are made daily.
I'm sorry, but the extreme claim that you're looking for proof of was never made. You are battling a strawman.
I, and likely many others in this thread, have tried our hand at trading. I've had months where I generated amazing profits. I have "algorithms." Yet I definitely don't pretend any of this stuff is special or noteworthy—why would Sebastian's be?
A huge part of what's cool about Indie Hackers is that people are generally transparent and you can see their approach to roughly similar problems. There are plenty of sites (hundreds of them) where you can find people bragging about their trading strategies and bots. Why does Indie Hackers have to expand into them?
This is nothing like the SubmitHub interview. That had lots of great lessons in customer development, building a brand over the years, etc. Realistically the only lesson from this story is "get lucky."
> In fact, I enumerated some of them as asides in the interview itself, none of which would apply to your hypothetical trip to Vegas.
Why not? I'm sure I could come up with some trite lessons about how poker playing is applicable to business and startups. Heck, there's a whole cottage industry in doing so.
That doesn't mean I think a story about my poker playing would make a good Indie Hackers interview.
> money-making machine has succeeded (answer: obviously not), and ignoring the actual point of the interview
What, exactly is the point of the interview then? You could just as well cover random sites that have launched with 0 profit or revenue. Heck, if you're in that business, I've got a ton of side projects I'd love to share.
I'm trying not to be too critical here, as I genuinely like Indie Hackers. But you need to have some standards for what gets included. Everyone who manages to make money doing something shouldn't count.
In this particular case, the amount of time and effort an 18 year old put into researching and educating himself about a difficult field is quite inspiring. As is his dedication to doing some non-trivial programming work and actually launching. That might not be inspiring to you or to professional traders on HN, but I can assure you that most IH readers will not care if/when his trading bot ultimately fails.
> What, exactly is the point of the interview then? You could just as well cover random sites that have launched with 0 profit or revenue. Heck, if you're in that business, I've got a ton of side projects I'd love to share.
I've featured lots of very small projects. My minimum cutoff nowadays is $100/mo, but in the past I've done interviews where the revenue was $0 or not shared. Although it's fun celebrating big revenue wins, that's not the point of the site. (If you don't believe me, I can point to numerous places where people have actually asked me to feature $0 failure stories on the site.) The point is motivation, inspiration, and education for getting around the most common obstacles that stand in the way of creating an online business.
I'd like to think I'm part of the core IH audience. I come for interesting stories of people building software from scratch and generating revenue from it.
Someone who got lucky gambling their money for a few months is just not an interesting story. It's way outside the mold of what you usually publish.
> My minimum cutoff nowadays is $100/mo, but in the past I've done interviews where the revenue was $0 or not shared. Although it's fun celebrating big revenue wins, that's not the point of the site.
It's good that you have a cutoff, but I think the issue is that this project doesn't necessarily meet that. With your typical interviews, you know they're making revenue from actual customers and that revenue is a meaningful metric. He happens to have generated profit so far, but I also happen to have generated profit on my gambling trip: it's not a meaningful metric, and in fact, might as well be 0.
He could easily have all his revenue wiped out next month (and, in fact, almost did). I'm really not sure what we have to learn from someone who has successfully gambled for a few months.
What I keep pointing out are the undeniably valuable lessons that can still be learned from what Sebastian did, as well as why a typical indie hacker might find them inspiring and educational, and why they wouldn't apply to your gambling analogy.
I'm not sure why you're ignoring these parts of my responses. Maybe it's because you've already launched many non-trivial side projects, so you aren't intimidated by that particular hurdle, thus you don't find it inspiring, and as a result you feel compelled to focus entirely on the efficacy of his product. Which is fine! But you are not everyone.
For my gambling, I too read books. I too wrote scripts and models to assess things. I too have practiced.
At the end of the day, I don't delude myself into thinking those lessons are applicable to my actual business.
The fact remains that many people never develop these skills, never get over these hurdles, and oftentimes don't even realize that these hurdles exist. They find it motivational to read about people who did. Especially a teenager like Sebastian.
And ofc you're right: Sebastian is no different than others who came before. But that's never been a criteria for being on Indie Hackers. I find it somewhat telling that the people who are up-in-arms about this interview consist almost exclusively of those working in finance or who've experimented with algorithmic trading.
I was trading stocks, it's really easy to fake even videos. You don't even need to fake it - just record everything and publish only successful deals.
If this story is true, it should be confirmed. Otherwise, the article can't be considered as serious.
Also you mention you had some concern that some of the stocks may crash. Have you worked in finance in the past to be familiar with the securities offered by the NSE, BSE and MCX?
Have not worked directly in finance, but I always had an interest in it. However I accumulated most of my experience in the past year. My recent concerns concerns were based on previously observed patterns and analytical observation.
And what api can be used for trading?
Are they expensive?
Do you have anything beyond "I'm making $3.5k using methods I won't disclose on an initial investment that I won't disclose"? What's your return on your investment? Sharpe Ratio? If you apply your investment criteria in historical data, do you beat the market?
How different is it from the guy who invested his tuition money on Tesla?
Hedge funds, for example, are largely black boxes, but the publish their returns.
I had a near 99% accurate scalping system. I could not believe it. Every trade I was making was profitable. How could this be?
The system worked without a stop loss. Meaning 1% of the time the prices turned, it wiped out all the profits (limited reward) accumulated.
I published all of these details on my university homepage which has since been deleted as they won't let alumni's keep one. But I was very careful that while 99% system accuracy is achievable, it's the downside risk that makes the system pretty fucking useless.
Of course you can put a stop loss but the system ran on "limited rewards unlimited risk". There's just no holy grail out there. Even if you read Hull's options book, no matter how complex your option strategy gets, you always have to be right at the end of the day. It's pure speculation and we all know how casino's work.
So knowing this, if it sounds too good to be true, there's a very strong reason for it. Retail trading is a zero sum game. Even more suspicious when the downsides are conveniently left to "if I gave it away system won't work". I was fully transparent about the downsides when I published my trading system.
The last thing I wanted was to people without the financial literacy to naively believe that a holy grail trading system existed. They don't exist. History is filled with funds that blew up because they believed alpha generation would be a constant thing.
Even quant trades I question their success. In the long run, all trades are speculative and carry risks (except arbitrages which are automated to oblivion). No matter how sophisticated you get the risks are always unknown.
Definitely feeling like this is faux..
Edit: Some pointed it is an Indian Marketplace - but the article mentions that Initrinio provided real-time data but Initrinio only provide IEX (https://intrinio.com/marketplace/data/prices/realtime)
The difference between gambling and trading is not that big. Trading has more ways where you can get an edge over the house, but it is not that different from poker or slot machines.
Trading is HFT. For anyone else, you should buy an index fund and never touch it.
Day trading is a really bad HFT and bad gambling.
As mentioned in the post, I only used it to train the models on, not to get the live quotes for trading.