Boosting models for algo trading
Stack Exchange Forum » Algorithmic Trading
by daniel dvali
5d ago
I’m currently working on a xgboost model to predict the price change above or below a given percentage between a candle’s open price and the next candle’s close price. I use a wide range of features, including market sentiment, unemployment rate, inflation, s&p ohlc data, as well as calculated technical indicators for the coins at hand. I have seen a recent article on achieving performance vastly superior to hodl on ETH and BTC with boosting models in particular (https://arxiv.org/pdf/2311.14759.pdf), but I’ve grown skeptical to whether these numbers could be achieved in practice. The ques ..read more
Visit website
IDE to use for Python for Quant Trading
Stack Exchange Forum » Algorithmic Trading
by Julien Maas
1w ago
Dear Quantitative Finance Stack Community, Since many Quantitative propietary trading firms seem to be using Python over alternatives such as STATA. I have now decided to get myself familiar with Python as well. Since I want to be able to write and edit scripts in an efficient and reliable way in Python, I was wondering what IDE (integrated development environment) people in this community prefer to use and why, when it comes to developing trading strategies, analyzing financial data and other related applications. I'll gladly hear from you, Kind regards, Julien Maas ..read more
Visit website
Where can I find live order book data for crypto with paper trading feature on the cloud for $50-$100 a month?
Stack Exchange Forum » Algorithmic Trading
by Deka Halane
2w ago
We're a startup creating an algorithmic trading bot for cryptocurrencies and looking for a website where we can fetch live, not historical limit order book (LOB) data for up to 100$ a month. I'd like to paper trade our strategy and need continuous live LOB data to do so. I've checked multiple website like Binance, Crypto Lake, Tradingview and Quantconnect. The latter offers a subscription that requires too many add-ons, the sum ends up at 300$! If anyone has recommendations, I'd be happy to check them out! Thanks in advance ..read more
Visit website
Given a statistical model which predicts price, how to determine trading strategy?
Stack Exchange Forum » Algorithmic Trading
by MilTom
2w ago
Let us assume that we have a statistical model such as ARIMAX that predicts the daily closing price of an asset for the next 30 days. Assume starting capital of $1mn. The model will make new predictions every day for the next 30 days. Usually the model will be more confident in nearer predictions and less confident in farther predictions and this is something we can quantify using predictive intervals. How do we decide the trading strategy and how much capital we should we allocate to each trade? For example, if the model predicts the price will be almost flat in the next 30 days and if our e ..read more
Visit website
Stock trading data across multiple vendors interview question
Stack Exchange Forum » Algorithmic Trading
by user70981
2w ago
I had the following coding question in a quant shop interview recently. I have no experience with quant finance, so I was hoping to get some insight on if this problem actually represents some real world trading problem. Essentially, the question was something like this: Suppose you have 2 vendors (can't remember if they used the term "vendor" or "exchange" but I don't think it matters for the problem) with different stocking trading data. Timestamps are given in the data. If the price and quantity are the same, then they're considered equal. This comparison can initially be done using a stat ..read more
Visit website
Bound on path length of a stock price
Stack Exchange Forum » Algorithmic Trading
by TryingHardToBecomeAGoodPrSlvr
3w ago
Consider a time series $(S_i)$ representing a stock price (say close prices of one minute candles). Let $\Delta$ be a quantization step (could be the price step in the strike prices of the corresponding options) and let $K \triangleq (\sum_{j=1}^{r} \lvert \lfloor (S_{i_j}-S_{i_{j-1}})/ \Delta \rceil \rvert)/(R / \Delta).$ Basically I have tried to define a measure $K$ that measures the number of times the stock price just crosses a certain strike price ($j$ times here) relative to the max and min bounds of that series during that day. Is it possible for us to have $K > 10$ (ten is arbitrar ..read more
Visit website
Mental math method for large integer multiplication
Stack Exchange Forum » Algorithmic Trading
by Xu Shan
3w ago
I am practicing for trading interview, especially the quick calculation of mental math. But I am wondering is there any quick method to calculate the general multiplication? like the one -4.41 * 2.86. I know some methods for 5.01*6.99, as (5+0.01)(7-0.01). But how can I calculate a general multiplication of two simple integers or common numbers? Thanks ..read more
Visit website
Guidance on Execution Algo Passive order placer?
Stack Exchange Forum » Algorithmic Trading
by VidhayakChacha01
1M ago
Could someone help with any relevant literature about building an Execution Algo and things to consider and keep in mind for optimal passive order placements? There are basic algos like TWAP/VWAP/POV etc, but how does one gain edge on the micro structure level? does it also involve understanding the microstructure better ..read more
Visit website
Trading strategy with only knowledge of price increase/decrease?
Stack Exchange Forum » Algorithmic Trading
by BeefJerky
1M ago
Take a hypothetical model that takes a stock as input and outputs "up" or "down" indicating if the stock price will increase or decrease in a fixed time interval T. Assuming the model is correct >50% of the time, what are the strategies to trade given this information? No indication of how much the stock increases/decreases so a simple buy strategy would obviously fail ..read more
Visit website
Potential problems with trying to apply reinforcement learning to algorithmic trading
Stack Exchange Forum » Algorithmic Trading
by QMath
1M ago
I have been attempting to develop an algorithmic trading agent for a single asset pair and upon researching, it seems as if, in theory, reinforcement learning would be a natural way to approach this problem. My idea was to have our observations be defined as follows: $$o_i = (t_i, v_i, w_i, b_i)$$ where $t_i$: time of observation $v_i$: amount held by agent of asset 0 $w_i$: amount held by agent of asset 1 $b_i$: some actionable representation of the market such as quote data or order book data for an order book market, asset reserve levels for an automated market maker decentralized e ..read more
Visit website

Follow Stack Exchange Forum » Algorithmic Trading on FeedSpot

Continue with Google
Continue with Apple
OR