For anyone playing the stock market, and perhaps even more so for those investing in cryptocurrencies, watching the value of your portfolio go up and down can be a stressful experience. If you’d like to have a real-time display of your investments that adds even more stress, [Luis Marx] has got you covered. His latest project is a plexiglass case (video in German) that fills up with banknotes when your portfolio is up, and shreds those same notes when it’s down.
Inspired by an infamous Banksy artwork, [Luis] began by building a wood-and-plexiglass display case suitable for hanging on the wall in his office. He then installed a small paper shredder, modified with a servo so that it could be operated by an Arduino. Unable to find an off-the-shelf banknote dispenser, he designed and 3D-printed one, consisting of a spring-loaded tray and a motor-driven wheel.
The project also includes a Raspberry Pi, programmed to fetch market data from online sources and calculate the net profit or loss of [Luis]’s portfolio. The resulting system is a rather disturbing visualization of the ups and downs of the market: having to sweep strips of green paper off your floor adds insult to the pain of losing money.
If you want a less painful way to keep track of your investments, try this Rocketship. For those interested in traditional stock tickers, this ESP32 based one might be more to your liking.
Continue reading “Banksy-Like Stock Tracker Shreds Your Money When The Market’s Down”
Machines – is there anything they can’t learn? 20 years ago, the answer to that question would be very different. However, with modern processing power and deep learning tools, it seems that computers are getting quite nifty in the brainpower department. In that vein, a research group attempted to use machine learning tools to predict stock market performance, based on publicly available earnings documents.
The team used the Azure Machine Learning Workbench to build their model, one of many tools now out in the marketplace for such work. To train their model, earnings releases were combined with stock price data before and after the announcements were made. Natural language processing was used to interpret the earnings releases, with steps taken to purify the input by removing stop words, punctuation, and other ephemera. The model then attempted to find a relationship between the language content of the releases and the following impact on the stock price.
Particularly interesting were the vocabulary issues the team faced throughout the development process. In many industries, there is a significant amount of jargon – that is, vocabulary that is highly specific to the topic in question. The team decided to work around this, by comparing stocks on an industry-by-industry basis. There’s little reason to be looking at phrases like “blood pressure medication” and “kidney stones” when you’re comparing stocks in the defence electronics industry, after all.
With a model built, the team put it to the test. Stocks were sorted into 3 bins — low performing, middle performing, and high performing. Their most successful result was a 62% chance of predicting a low performing stock, well above the threshold for chance. This suggests that there’s plenty of scope for further improvement in this area. As with anything in the stock market space, expect development in this area to continue at a furious pace.
We’ve seen machine learning do great things before, too – even creative tasks, like naming tomatoes.
In the financial sector, everyone is looking for a new way to get ahead. Since the invention of the personal computer, and perhaps even before, large financial institutions have been using software to guide all manner of investment decisions. The turn of the century saw the rise of High Frequency Trading, or HFT, in which highly optimized bots make millions of split-second transactions a day.
Recently, [Wired] reported on Numerai — a hedge fund founded on big data and crowdsourcing principles. The basic premise is thus — Numerai takes its transaction data, encrypts it in a manner that hides its true nature from competitors but remains computable, and shares it with anyone who cares to look. Data scientists then crunch the numbers and suggest potential trading algorithms, and those whose algorithms succeed are rewarded with cold, hard Bitcoin.
Continue reading “Hedgefund Startup Powered By Crowdsourced Code”
[Johna and Justin] are working to take the emotion out of playing the market. They built this piggy bank which automatically purchases stock when your coinage totals the cost of a single share. That’s right, just turn the selector to one of your three chosen stocks (Google, Facebook, and Apple are used in this example) and plug in some coins. The bank counts your money, compares it to the current online stock price, and pulls the trigger if you have enough dough. You can check out a demo clip after the jump.
The hardware is rather simple thanks to Adafruit’s programmable multi-coin acceptor. It handles the cash and it’s pretty easy to interface with the Arduino which handles the rest of the work. It connects to a computer via USB, depending on a PHP script to poll the current price. We dug through the code repository just a bit but didn’t find the snippet that does the actual stock purchase. Whether or not they actually implemented that, it’s certainly an interesting concept.
Continue reading “This Piggy Bank Is Our Stock Broker”
If you can’t help but spend the day checking in on your stock prices this ambient device can help you cope. It monitors how the trading is going and illuminates an LED as feedback. Here the Apple stock is trading up so the light is green. The video after the break shows other stocks trading down, causing it to switch to red.
An Arduino interfaces with the custom application via USB. For now it looks like the two colors are all it’s capable of but we think there’s a lot more potential. Some creative coding could use factors like how much the stock has moved, trading volume, volatility, or a plethora of other data to give feedback. We could see a spectrum of colors (like on a temperature map) used to improve the level of feedback. And if the market really tanks there’s always the ability to add flashing!
The diffuser for the project is quite interesting to us. [Ali Reza Kohani] made it from a leftover scrap of acrylic. The bubbled surface was created with a heat gun before bending the sheet into an arc.
Continue reading “Stocker Monitors The Markets”