Building a $3,500/mo Neural Net for Trading as a Side Project

5 stars based on 49 reviews

I'm Sebastian Dobrincuand I'm a software engineer currently working as a freelancer. I'm also an avid product maker who loves building side businesses and crazy projects. I initially built Stock Trading Bot as a personal research project.

I was testing the waters to see if modern machine learning approaches can be used to predict and automate selling and buying of assets in today's stock market, at a much more efficient rate. Currently I am the sole user. I'm planning to continue working on it with the goal of scaling the bot as much as possible. The idea popped up pretty randomly.

I was getting ready to board a flight to SFO and decided to download some podcasts. I felt like trying something new, so I picked a few of the most popular ones from the Finance category. The host brought up the topic of liquidity, which boils down to 3 measures: Essentially when liquidity is high, investors can successfully trade a larger order close to the current price and within a short time span. Once they began debating whether or not high frequency trading was improving the market by providing liquidity, I switched to the Notes app on my phone and started furiously typing some of the main ideas.

Prior to this project, my experience with finance in general was pretty limited. I had a solid understanding of the fundamentals of trading but not much beyond that. The first one is probably the best piece on finance I've ever read. It literally answers all those questions any curious person who has ever made a trade might ask. On the other hand, John Hull's book gave me a fantastic introduction on mathematical finance from an applied point of view.

I highly recommend both if you are just getting started with trading. I believe we've reached a peak in the field of AI. We now have both powerful machines and enough data to process. With this in mind, my inner engineer got excited at the possibilities of tackling the market with today's advancement in technology.

Besides that, I have an addiction for creating fascinating projects and this was no exception. The huge advantage is that you are not necessarily starting with a handicap against the big trading firms. That's because when it comes to stock trading, even microseconds could make trades go wrong — such as your bot falling victim of a faster bot's bait offer. And guess who owns the faster servers and bots? With cryptocurrencies however, these small time increments are not nearly as important.

Although I believe it's the golden age to be in the Bitcoin market because it's imperfectI quickly abandoned the idea maybe too quickly? Without boring you with technical details any longer, the solid trading APIs were mostly based on REST, which is not fast enough for what I was aiming for. 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.

Long story short, I ultimately ended up going for the stock market, but not into high frequency trading in its real meaning. My bot holds a single position from seconds to minutes sometimes even hourswhich makes it more of an automated trader than a high frequency trader.

The reason behind this is that being an individual trader makes it extremely hard to compete with the big guys, as you're lacking perks such as very powerful hardware, advance trained software, and great locations for your servers.

The closer to the stock exchange you are, the faster you receive the information. Large investment servers are literally paying millions to get their servers a few miles closer to the exchanges. 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. I built the first prototype in a little under a month. I was working late hours, trying to find time around my daily job as a freelancer. At this point the bot wasn't very smart. It took me about 2 more weeks to feed it with data until my error rate was satisfactory, and another 2 weeks to test it before putting it in production.

Summed up, the technical implementation of the current version took about 4 months, with some more improvements along the way. Since I publicly announced itI've been receiving dozens of offers from trading companies. At the moment the system gives me an edge over other traders. If I sold it, I'd be giving this advantage to other traders and, subsequently, losing my lead. Although I do not exclude a future buyout, I am presently focusing on improving the product and trying to scale it.

One of the things that I plan on doing soon is increasing the capital and therefore putting the bot through more trading volume.

There are tons of improvements I have in mind, especially on adjusting the position-holding time span, as well as solutions to make it more lightweight, facilitating larger volumes.

I wasted way too much time trying to apply high frequency trading in Bitcoin. At first the idea sounded great, but I was soon facing a lot of technical issues trying to scale the amount of requests. However, I am not yet convinced that it's impossible to achieve true HFT with cryptocurrencies, so it might be something I come back to in the future. After drifting away from the idea of HFT due to the technical limitations, I looked into a more analytical approach in automated trading.

Most of those concepts couldn't be applied in the Bitcoin market, as it's highly unpredictable, making it hard to shape the models around it. That's when I decided to stick to the stock market.

Another big mistake in the beginning was relying too heavily on models. Instead of trying different approaches in analyzing the data I had, I relied solely on the models for identifying profitable patterns without investing time into other more direct solutions.

Models are only simple real world abstractions, and my common sense has saved me more than once. 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.

I learned this the painful way. Not too long ago the market went pretty crazy, and I'd be lying if I said that I wasn't expecting some major crashes of the stocks I was trading.

Although my stop-loss saved me from some brutal losses, had I not stepped in at the right time, the bot would've ruined all the profit from the past months. That event really got me thinking, and I decided to stop it running for a few days until I fixed that loophole. This was also a great learning experience for me, and I believe that without going through those ups and downs, I would've never managed to get the algorithm to where it is today. I have no regrets losing time on Bitcoin, as it gave me a deeper understanding of how cryptocurrency trading works, which might prove useful some day.

Probably my biggest single advantage is being a starry-eyed young dreamer. To some extent, this allows me to believe enough to put effort into ideas in that others wouldn't. That's what motivated me to persevere in finding those "backdoors" in the market. While many people believe individual traders don't stand much of a chance against the well-equipped companies, I am here to prove that with the right implementation there still is plenty of space in the market.

Another immensely helpful resource were the public research papers available online. In fact, I got tremendous help from papers published back in I often found that most of them are easily overlooked, although they contain super useful analyses. Being a workaholic has also contributed a fair amount to this success. I have no issue whatsoever working hours per day. With time, I developed a very productive and consistent lifestyle, managing to get rid of most distractions.

This allowed me time to invest in polishing and researching the different strategies for this project. If you've worked your butt off to build something and give up on launching it, no one will care about it. We live in a very capitalist society where people will judge you based on real results.

No one cares about your initiative and the reasons why you didn't launch. As Sam Altman says, nothing will excuse you for not having a great product. However, not having anything is certainly worse than that. Don't make it perfect from the first version. Test the market first, gather tons of feedback and constantly iterate over your idea. Although this is not necessarily a customer-focused product yet? Side projects allow you to experiment on crazy ideas without being labeled as crazy.

And definitely go for the craziest idea you have in mind. That's how most of the successful companies started talk Facebook, Uber, AirBnb. Every problem has a solution. You just have to be creative enough to find it.

I am currently available for freelance work. You should join the Indie Hackers community! We're a few thousand founders helping each other build profitable businesses and side projects. Come share what you're working on and get feedback from your peers. Not ready to get started on your product yet?

Solid gold casts of nelson mandelas hands sell for $10 million in bitcoin

  • Browser miner bitcoin czech republic

    Buy bitcoin with western union online

  • Basic 02 bitcoin mineral

    Ethereum blog dao duyen

Unspent bitcoin values

  • Auto bot like status for fb

    5000 gh s free mining bitcoin mining fast how to earn bitcoins for free2018

  • Robo tron x robot ironman

    Where should i invest my bitcoin

  • Bitcoin servers for sale

    Fx 797a tdkc litecoin exchange rate

First bitcoin website

45 comments Bitcoin mineri mine for bitcoin and show others how

Small liquid ring pump dead

I was a day trader for many years and it almost killed me. I made money by making profits on my own money and also taking a percentage of the profits for the people I traded for. I did this from to I learned about day trading but I also learned a lot about myself and what I was good at, what I was horrible at, and what I was psychotic at.

Things that had nothing to do with day trading. Day trading is the best job in the world on the days you make money. You make a trade, then maybe 20 minutes later you are out of the trade with a profit, and for the rest of the day you think about how much money you made.

I would make a trade, it would go against me, and then I wanted my heart to stop so my blood would stop thumping so loudly. All of these lessons I will certainly use today, many years after I stopped day trading. This applies not just to trading but everything. You could be married for 10 years and the next thing you know you are divorced and you would not have predicted that.

You could be healthy all your life and drink your vegetables and exercise and reduce stress, and a year later you could be dead from cancer.

You can always seek to increase the odds in your favor. But certainly a path to unhappiness is thinking the future can be predicted and controlled. A hundred percent of opportunities in life are created because people are uncertain about almost everything in their lives. We are constantly trying to close the enormous gap between the things we are certain about and the things we are uncertain about, and almost every invention, product, Internet service, book, whatever has been created to help us close that gap.

Sometimes this is hard. If your husband betrays and leaves you, you often feel like crawling on the floor and burning all the self-help books. You can say it something inside of yourself. Some people take too many risks and they go bankrupt. This happened to me. But then I would take big losses and that would wipe out all my profits.

The key is that you can take larger and larger risks if you work on better and better ways to deal with those risks. For instance, I might be able to risk marrying someone if I know she is not a hard-core drug addict who regularly betrays the people she is close to. I can risk driving without a license if I always stay below the speed limit I know this is a stupid risk, but still. How can I get that job? When I was raising money to day trade, I probably contacted over 1, people.

When I was starting an Internet business I started over a dozen Internet businesses and watched all of them fail but one. When I was trying to sell my Internet business I contacted over a dozen companies although Google broke my heart — damn you Google! When I wanted to get married, I went on lots of dates. She would only go to tea with guys. Within the first 20 seconds you know if you are attracted.

So keep it to a tea. But this is just a mental bias. Say no to it. Day trading pulls everything out of you. It sucks the soul out of your body, blends it up, and then explodes. So you have to take care of yourself. And obviously, this applies to everything else in life. Every day, what small thing can you do to become a slightly better you? The only way to survive is to laugh. Guy makes a trade. The market goes against him. And then he loses all his money and goes crazy.

The market is never crazy. The world is never crazy. And I will go so far as to say that your girlfriend who just lied to you about where she spent the night is not crazy. I only care about you. Good and bad days happen. But life is about a billion little moments that add up to all the things around you. If you let one of those moments have too much control then you are bound to be mostly miserable.

I was mostly miserable during the period I was day trading. I let that aspect of my life take control. So I stopped focusing on being a good husband, a good father, a good friend, a good anything. I would have nightmares. I would lose sleep. I would wake up many mornings and go to the church across the street so I could be by myself and pray. What would I pray? So what makes anyone think they will have an edge? How many people listen to me? Because people are sick of their lives, their relationships, their jobs, and all the lies that have been told to them ever since they learned how to walk.

Day trading is the dream. You can make enough money to not care. To do it from anywhere. Most people think they have that one special something that will make it work for them. You can skip right to the being happy part. You can skip right to being free. But we never learned that. We were taught we had to do something first to earn freedom. We were taught that suffering was the currency to buy happiness. Okay, go do it. Then cry about it.

Then curse the craziness. None of that will make you happy. Then read this blog post again. Not because it will make you happy. But because I like when people read my posts. I was a day trader for many years, and it almost killed me. I did it for years, though, because I was unemployable in every other way.

Everyone thinks they can. B Hope is not a strategy. I hope that every day my life goes perfectly. C Uncertainty is your best friend. D Taking risks versus reducing risk. You have to decide every moment if this is the situation you want to be in.

All of my other constituencies went to hell. Nobody answered my prayers. They want freedom from the BS.