TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Building AI Trading Systems

215 点作者 dennybritz将近 5 年前

16 条评论

henning将近 5 年前
I tried doing some forecasting with various neural network models after assembling what I thought was a good amount of forex data. The neural net (I tried various architectures) couldn&#x27;t do any better than chance. After playing around with it and trying to double-check everything, that was as far as I could get. This puts me ahead of most traders, since most of them lose money, then quit.<p>This makes me wonder what kind of trading systems can actually have any kind of edge, since some kind of autoregressive time series forecasting system seems pretty unreliable.<p>On a more general note, how do you move beyond it being gambling? Just because a system backtests well doesn&#x27;t mean a phenomenon will continue to happen, especially if your system will significantly impact the market you&#x27;re in. If you make a trend-following system, every time you trade, you&#x27;re gambling that the trend is more likely to continue than not. If you&#x27;re right, you&#x27;ll come out ahead over many trades. If you don&#x27;t have enough capital to withstand drawdown the way most beginners don&#x27;t, you won&#x27;t be able to last long enough for whatever phenomenon you&#x27;ve found to average out.<p>It takes a lot of time, effort and risk to do all this, so, this is a long-winded way of saying I don&#x27;t think it&#x27;s for me. If you build a SaaS product and it fails, at least you can talk about what you learned from building it and use that in future endeavors. If you lose money trading because your algorithm doesn&#x27;t work, what do you learn from that besides that your algorithm doesn&#x27;t work?
评论 #23658834 未加载
评论 #23658432 未加载
评论 #23658236 未加载
评论 #23659825 未加载
评论 #23659475 未加载
评论 #23660091 未加载
评论 #23660878 未加载
评论 #23659082 未加载
评论 #23664112 未加载
评论 #23662978 未加载
anonu将近 5 年前
Just a reminder: nobody ever wrote about their super successful trading strategy. Its just never happened. If you have the wherewithal to research and build a trading system that works, then you&#x27;re smart enough to know that the moment you reveal your edge to the world - it disappears. Even if you dont discuss the innards of your strategy, but you talk about your process or the system youre strategy is built on, you&#x27;ve revealed too much.
评论 #23659732 未加载
评论 #23659188 未加载
评论 #23660154 未加载
评论 #23659123 未加载
评论 #23660310 未加载
评论 #23659654 未加载
halfcat将近 5 年前
I find most of this article to be “successful people can’t explain why they are successful so they say a bunch of arbitrary things they’ve noticed”.<p>He found success pursuing relative advantages, infrastructure advantages, and building custom tools from scratch.<p>But absolute vs relative advantages, plumbing together canned solutions vs building your own from scratch, infrastructure-level advantages vs decision making advantages...all of those contrasts exist in other businesses everywhere. None of those are specific to trading.<p>&gt; “in my experience, nothing beats learning by doing or finding a mentor”<p>This hits the nail on the head.<p>The best way to become a profitable trader is with a mentor, but it’s nearly entirely luck. You drive an Uber or tend bar and happen to make friends with someone successful who is willing to guide you. Trying to seek out a mentor online is nearly impossible, as everyone who is findable and willing is almost certainly a better marketer than trader.<p>The other way to become a profitable trader is to start trading with real money. It’s amazing how quickly one can learn how to mend a boat, when the boat starts sinking.
shoo将近 5 年前
readers may also be interested in Benter&#x27;s paper &quot;Computer Based Horse Race Handicapping and Wagering Systems: A Report&quot; -- <a href="https:&#x2F;&#x2F;www.gwern.net&#x2F;docs&#x2F;statistics&#x2F;decision&#x2F;1994-benter.pdf" rel="nofollow">https:&#x2F;&#x2F;www.gwern.net&#x2F;docs&#x2F;statistics&#x2F;decision&#x2F;1994-benter.p...</a><p>&gt; This paper examines the elements necessary for a practical and successful computerized horse race handicapping and wagering system. Data requirements, handicapping model development, wagering strategy, and feasibility are addressed. A logit-based technique and a corresponding heuristic measure of improvement are described for combining a fundamental handicapping model with the public&#x27;s implied probability estimates. The author reports significant positive results in five years of actual implementation of such a system. This result can be interpreted as evidence of inefficiency in pari-mutuel racetrack wagering. This paper aims to emphasize those aspects of computer handicapping which the author has found most important in practical application of such a system<p>Arguably the paper describes the state of the art from three decades ago, applied to betting on Hong Kong horse races, not market price movements.
评论 #23659164 未加载
评论 #23658613 未加载
rezahussain将近 5 年前
Writing ai trading systems is the coding I do for fun since 2012. I&#x27;m a little under break even so far but I keep at it because find it so interesting. Since I started every single week I have learned a new way of thinking about a problem I encountered or a new approach to problems that still stand in my way.<p>Questions like, how do you choose a stoploss? Well you can pick it statistically based on history or you can use a supervised label. You can even use stock A calculated stoploss to pick the stoploss you use on stock B because you found a condition under which those two stocks became almost identicall correlated. How do you want to pick the supervised label? You can do spectral analysis to pick the stoploss too. You can use sentiment as a stoploss, source from google news or twitter or stocktwits.<p>It doesn&#x27;t have to be, &#x27;well I measured the average profitable stoploss to use over the last 10 years across all stocks and that isn&#x27;t working so I quit&#x27;<p>Things like that, you get to fit the ideas together and then test them in the real world.<p>There are some things I would like to share.<p>1. Just because you have a good forecast doesn&#x27;t translate into cash. It has to be paired with a trading strategy. This is probably why the author thinks the answer is RL, because coincidentally if you approach this problem with RL, it does the forecasting + strategy.<p>2. I have measured a correlation between heavier processing(using a higher big O) and better out of sample performance.<p>The criticisms with the NN approach like non stationary data have obvious solutions that a &#x27;by the book&#x27; trading approach + ml approach don&#x27;t really teach beginners so they dismiss it.<p>It is my belief right now that there are people who are prepping data from sources like iextrading then using things like sagemaker to develop good enough forecasting and combining it with a statistics+rules based trading strategy to make living wages.<p>That said, I have 5k account size for my NN obsessions, and my 401k is &#x27;by the book&#x27;.<p>person_of_color is totally right when he says it is a Moby Dick of programming.
评论 #23659721 未加载
评论 #23658788 未加载
person_of_color将近 5 年前
Don&#x27;t do this. It&#x27;s the programmers Moby Dick. You are better off self learning stats&#x2F;ML skills in your free time and joining a quant fund than to try and do it yourself.
评论 #23659384 未加载
DoctorOetker将近 5 年前
I would love to try trading as a hobby with a little side money, but I would abhor a hobby that reduces to effectively buying the trader-feel-good experience, where you&#x27;re essentially sponsoring incumbents as a fanboy chipping in his pocket money.<p>What I would require from a trading platform:<p>1) decentralized and permissionless 2) provably fair trading<p>With &#x27;provably fair trading&#x27; I mean the protocol should be such that I can prove you are not simply held captive by an intermediary, regardless in what shape or form. It should also be fair with respect to latency.<p>For example consider a trading market where token X can be exchanged for token Y and vice versa. Each holder of X demands her minimum of Y per X, and each holder of Y demands his minimum of X per Y. What if everyone salty hashed their demands, and pays the market contract (proportional to how much they will actually be allowed to trade) to register their salted hash. When the round has closed, people reveal their salt and plaintext, and the incompatible trading offers get their money back (minus a usage fee perhaps). The compatible ones can have their trades go through at the rate of &#x27;total compatible X offered&#x27; to &#x27;total compatible Y offered&#x27; (or some variation thereof, say rewarding those that helped close the gap). In this way there is no high frequency trading, and you could have a family of such markets operating at different timescales...
mfalcon将近 5 年前
I&#x27;ve never tried the AI trading path but I imagine that you can&#x27;t get huge gains with public data, unless you find a way to extract &quot;hidden&quot; information by processing real time news.<p>I wonder nevertheless if there&#x27;s a sweet spot where you can build a simple AI trading algorithm and get modest earnings from it.
评论 #23659629 未加载
评论 #23659229 未加载
pinouchon将近 5 年前
For the last year or so I have been working on a ML-based trading system in the domain of crypto with two friends. I made more in 2 months than I used to in a year. This is after thousands of &quot;full positions swings&quot; and millions of trades (short and long). We are now experimenting with different classes of trading strategies to reduce risk.<p>We would like to find 1 or 2 more people to work on this project, we need people who can tolerate risk and skilled at data engineering: data pipelines, psql, pandas, numpy, data visualisation, setting up servers. Ideally also skilled at machine learning &#x2F; deep learning and who has tried his hand at trading systems. If interested, my email is in my about info.
thedudeabides5将近 5 年前
&quot;Actually, many months my PnL graph looked something like this: (this is generated to get a point across, but my real data looked extremely similar):&quot;<p>I&#x27;d love to see the actual data
star-trek-fleet将近 5 年前
What&#x27;s the real performance of the system so far?
评论 #23657898 未加载
mraza007将近 5 年前
Just curious to know do financial firms have implemented something similar to this
评论 #23659636 未加载
MichaelRazum将近 5 年前
To be honest. I don’t believe a word about the performance using AI. Especially if the article doesn’t present the features and the NN architecture. Its always the question: would a super simple model perform the same way? And very ofter the answer is yes.
评论 #23660136 未加载
linus_torvalds将近 5 年前
&quot;Then, profits started decreasing and I decided to move on to other things and I lacked the motivation to go back into it.&quot;<p>Is this post about the one with decreasing profits, or a new one that is profitable?
评论 #23659106 未加载
known将近 5 年前
trading != investing
dilandau将近 5 年前
In some markets it is necessary to put the same length of fiber-optic cable between the colocated servers, so that being closer to the exchange&#x27;s cabinet doesn&#x27;t translate into an advantage. So obviously we&#x27;re talking about extremely low latency, high-frequency trading. This carries a huge amount of prerequisites to even get started.<p>Not only are that, but there are many different order types besides &quot;buy at market price, sell at market price&quot;. Then there&#x27;s options, short sales, and more.<p>It goes deep. People devote 30 years of their career to this. Read the authors experience as a kind of warning, if you will.
评论 #23659701 未加载