Questions tagged [algorithmic-trading]
Algorithmic trading is the process of taking in inputs such as market data, current news, and producing orders without human intervention.
230
questions
-2
votes
0answers
34 views
how to find out the best model in algotrading using LSTM neural networks?
I am working on a simple LSTM Network that predicts stock prices in a 15 Min interval, I searched a lot and found the example shown in the Image, Which ends with some good predictions on my data set (...
1
vote
1answer
132 views
Rogers Satchell Volatility
I am trying to implement Roger Satchell volatility in Go, but my results do not match reality... I have been at this all day, but cannot find my error. The 30 day Rogers Satchell vol is at 8.75%, but ...
1
vote
1answer
73 views
Moving Average Window Size Determination
Is there a "correct" way of determining a moving average window/smoothing parameter (or at least a starting guess for a financial time-series?
I understand of course that in some sense, ...
0
votes
0answers
24 views
When developing an algo code with Interactive Brokers: which instruments to take during the weekend for testing orders and live data?
I am developing a trading algo that will use Interactive Brokers.
Presently I use my paper trading account but face the difficulty that during the weekend the exchanges are closed.
Are there any (...
0
votes
1answer
97 views
Kelly Criterion at the individual trade level or the broader trade rule?
Suppose I've raised some initial capital, $C$. I would like to invest it according to three different trading rules, $T_1$, $T_2$, and $T_3$.
Each of these rules will yield several trades over the ...
2
votes
0answers
48 views
Known methods for big order detection
I have an access to the order book from stock market and i am interested in finding an anomalous behaviour.
What are the known methods, algorithms for detecting big orders or other activities of ...
2
votes
1answer
135 views
python library for backtesting buying and selling multiple cryptos
What is a good python backtesting library to use if I want to test buying and selling a list of different cryptocurrencies every day? Most libraries I find like backtesting.py and pyalgotrade are ...
0
votes
1answer
77 views
Historical Options data
Are there any good sources where I can obtain daily historical options data (strike price, expiration dates, bid/ask spread, etc).
I understand that this type of data is very hard to come by and ...
1
vote
0answers
63 views
In Avellaneda-Stoikov market making, what is the difference between "reservation prices" and "optimal bid ask quotes"?
Question
What is the difference between "reservation price" and "optimal bid and ask quotes"?
Are they the same thing?
(1) Reservaton price
In the paper High-frequency trading ...
1
vote
0answers
64 views
Market making algo using bid ask order volume ladder
I am looking for references for market-making strategies using bid-ask order ladder. Algo should suggest entry prices, and do inventory management. I am more interested in practical simple algo used ...
0
votes
1answer
64 views
YFinance incoherent daily and hourly values
I'm comparing daily and hourly values extracted from YFinance in Python.
I'm expecting the open value of the first hour of the market to be equal to the daily open value of the corresponding day, and ...
0
votes
0answers
31 views
Variable Position Sizing: Equity Curve vs Buy & Hold
I have a trading strategy that can take multiple long positions with different sizes before selling them. For example, buy 5 shares of ABC on days 1, 2, 3 and sell 15 on day 4. Going forward, buy 10 ...
1
vote
0answers
31 views
What types of messaging middleware solutions are used by the biggest exchanges like Nasdaq, NYSE, ICE, NYMEX, Japan Exchange Group, Euronext, etc?
Exchanges are famous for having to deal with a huge amount of messages. For example, some years (decades?) ago Nasdaq has migrated their reliable UDP protocol from 32-bit, which could support sequence ...
5
votes
1answer
295 views
Modelling queue position
Is there any viable way for me to know the dynamics of my LOB position? Lets suppose the LOB is order based LOB, and i send a order to this level, can i know if the qty in front of me cancelled vs ...
1
vote
0answers
81 views
OLPS in real conditions
The Online Portfolio Selection problem has been extensively researched over the years, and various models have been implemented in open-source projects on GitHub. However the theoretical frameworks of ...
0
votes
0answers
78 views
Train/test: why 80:20 split performed better than 90:10 split?
Playing with Random Forest Classifier, I am wondering what could cause in a 80:20 split the test results to perform better than in a 90:10 split?
With 2000+ data points and:
with 80:20 split, ...
0
votes
1answer
65 views
benchmark scalping strategy in timeseries
I've a trade data for set of portfolios to analyse. I'm looking for simplest (most efficient but deterministic way) to calculate and find best scalps during a trade day. Criteria are pretty ... ...
0
votes
0answers
49 views
What are the best books or sites to learn to spot algorithm actions
12 years ago Alan Farley in The Master Swing Trader Toolkit wrote about how to spot the footprints of algorithms such as incremental steps in price through a gap and how algorithms push price down ...
1
vote
3answers
635 views
If 90% of retail traders lose money, doesn’t that mean price movements are not random?
If 90% of retail traders are said to loose money, which trade in the short term, doesn’t that mean price movements are not random?
My reasoning is that if short term price fluctuations were ...
4
votes
1answer
261 views
Ensuring market order creation idempotency
I am trying to find a way of placing market orders on crypto exchanges in an idempotent way. Specifically, I want to ensure that retrying the same request does not cause another order to be placed. ...
0
votes
0answers
89 views
Backtesting trading algos using simulated price instead of historical prices
I don't have any real experience in trading. I have a question in my mind for which I can't convince myself.
Why do we need real history price data to do back-testing?
In my mind, real data is only a ...
0
votes
0answers
59 views
Convert stock symbols so that they are useful for Yahoo Finance (yfinance)
I am working on my first investment algorithm, and I am using the following list of stock symbols and company names:
https://public.acho.io/embed/...
1
vote
0answers
39 views
Exchange order matching system/core for local testing
I am looking for a service that can be deployed locally or connected to it and would emulate the order matching system of exchange (a.k.a matching core).
I remember, that I have seen on GitHub repo, ...
0
votes
1answer
217 views
What is the quickest way to start a database for algo trading from scratch?
Many people who are interested in algo/quant trading must have faced the same question before: how do I set up my own database from scratch?
I think much effort has been duplicated when we brainstorm ...
2
votes
1answer
344 views
Formerly profitable algorithmic trading strategies?
Since algorithmic trading strategies often stop being profitable after a while, I wonder if any such formerly profitable strategies have been made public, and if so, where can I find them?
8
votes
2answers
2k views
How long do algorithmic trading strategies typically remain profitable?
As I understand it, an algorithmic trading strategy could lose profitability, if, for example:
it's rediscovered by others
employee turnover leaks the strategy to others
market conditions change ...
0
votes
1answer
117 views
Steps to fit a Machine learning model for prediction of up and down market movement
I have around 5 years of data of an index containing many features on a daily basis. I want to classify whether the index will move up or down the next trading day (up or down movement is determined ...
2
votes
1answer
525 views
What are the "sniffing" or "stalking" algorithms?
I was looking for all the sorts of trading algorithms used in stock market and I came across the so-called "sniffing" algorithms. However, the explanations of this concept I found are very ...
0
votes
0answers
76 views
Effectiveness of trading strategies
Generally, a trading strategy is effective for a certain duration which is a function of the environment, news etc. I am currently learning about basic strategies that are (or once were) used. Some ...
0
votes
0answers
107 views
Pairs Trading Strategy Pre-Selection
I am writing paper on the profitability of the pairs trading strategy using US equities. I have done a pre-check to see which business sectors have stocks that are cointegrated. The utilities sector ...
1
vote
0answers
110 views
Pairs Trading (Cointegration Approach) - Daily Cointegration Test
I have a question regarding the Pairs Trading strategy based on the Cointegration Approach.
Most of the papers/literature I found on Pairs Trading using the Cointegration Approach are usually testing ...
0
votes
0answers
40 views
Strategy in mql5
I have the following code(is not mine) in an Expert Advisor:
if((Handle(DXHandle, 0) - Simbolo.Ask()) >= (DXPontosDistancia * _Point)){...}
Handle(DXHandle,0) ...
2
votes
3answers
424 views
Python library for tick-based backtesting on cryptos
I saw and reviewed many python backtesting libraries - pyalgotrade, zipline, catalyst, backtrader, etc.
It seems that none of the provide a straightforward way to perform "Tick-based or Multi-...
0
votes
0answers
16 views
Understanding additive profit of risky and risk free asset
I was going through paper "Learning to Trade via Direct Reinforcement" by Moody and Saffell. It explains additive profit as follows
Additive profits are appropriate to consider if each ...
1
vote
1answer
77 views
How to Manage Large Orders
Forgive me for any violations of posting rules, I’m new to this forum.
I’ve written an algorithm that checks the order book for the price point that would completely fill my entire available balance, ...
2
votes
0answers
197 views
What theory and philosophy is algorithmic trading based on?
I work in model validation and I am familiar with classical investment strategies, economic theories and pricing models of options and I am curious about algorithmic trading. What is it driven by? ...
1
vote
0answers
177 views
How do you detect order execution algorithms?
Most large orders nowadays are done through TWAP or VWAP based order execution. For example, if Alice wants to sell $60 million in EURUSD she will break up her order into 50,000 tiny orders and then ...
2
votes
3answers
559 views
Deep Reinforcement Learning in Quant Finance?
I've been struggling to find engaging papers on the application of deep reinforcement learning in quantitative risk analysis, portfolio management, algorithmic trading and/or options pricing. What are ...
0
votes
0answers
36 views
How to deal with outliers when normalizing price related input in algorithmic trading
I am training a CNN model for trading using indicator and MA lines to compose a 2D array as input. I want to normalize MA data(ema, sma...) into range between -1 and 1, I have tried several techniques ...
0
votes
1answer
31 views
Why does historical equity ticks from Dukascopy.com not contain trade ticks?
I've found that ticks for equities (for example for companies from US market like Amazon or Apple) someone could name as "best bid/ask offer" (or Level 1 type of tick data) and them clearly ...
2
votes
1answer
164 views
What should the look-back period be when calculating Cointegration?
So I am confused as to what the look-back period should be when calculating Cointegration. By this I mean when running for example a Johansen or ADF test, should my look-back period be 6 months?...
0
votes
0answers
46 views
How to understand the results of the Johansen test?
So I now there are numerous pages on the johansen test, and what the results mean. Though I am confused as to what it is doing exactly. So my understanding is that it will find the spread of 2 ...
1
vote
1answer
87 views
Should I calculate a spread using stock prices or the ratio?
So I am creating a trading algorithm thats uses cointegration, for a pairs trading strategy. Imagine there is stock A for 100 dollars and stock B for 25 dollars. My questions is when caulcating the ...
0
votes
1answer
143 views
The quality of an trading algorithm
Good day. I am currently writing a term paper on the creation of trading algorithms in the foreign exchange market (by an algorithm I mean the one that follows the alpha model, for example, signals ...
1
vote
1answer
333 views
Tactical Investment Algorithms
I am reading paper "Tactical Investment Algorithms" (link) (NOTE: you can download the paper without registration, just press "Download" and then "Download without ...
1
vote
0answers
139 views
Machine learning algorithms that generate trading models (literature)?
Is there any academic literature on machine learning algorithms that are able to generate functioning trading models? Would this even be feasible at all, now or in the future? Could you point me to ...
0
votes
0answers
56 views
Cumulative returns from ROI of individual trades
I've a series of ROIs: $R(n) = [r_1, r_2, ... r_n]$ generated from taking $n$ trades. Each ROI value is in percent $[0, 1]$. How do I generate cumulative return $C(n)$ from this data?
My understanding ...
0
votes
0answers
50 views
Managing fund of bot users
I'm algotrading since 2018 and been profitable (not much, but consistent) since then.
This year I thinking in make a business around this bot. My only doubt is how do I manage the fund of all users? ...
0
votes
0answers
41 views
Computing Sharpe ratio correctly when adding more funds
I've a very basic question:
Assume, as time $t_0$, I started a algorithmic trading strategy with initial capital $X_0$. My strategy on subsequent $N$ time frames generated returns $r(t_1), r(t_2),..r(...
0
votes
1answer
154 views
What kind of option would best be suited for a price based algorithm?
So say I wanted to make money off of a simple RSI-MACD algorithm on SPY (ofc this may not necessarily make money, but let's say it does). I'd like to leverage my returns using call and put options, ...
