Questions tagged [machine-learning]

Algorithms that allow computers to evolve behaviors based on empirical data. Approaches include genetic programming, artificial neural networks, decision trees, support vector machines, and cluster analysis.

Filter by
Sorted by
Tagged with
1
vote
1answer
46 views

LSTM for trend prediction

Been wanting to get my hands dirty with ML for a while now and since I'm interested in finance and trading as well, I figured this would be a good project to get started after reading Deep LSTM with ...
1
vote
0answers
22 views

Looking for references on reinforcement learning in finance

I plan on using reinforcement learning for a research project. To be specific, I plan to define learning environments using market microstructure models whose solutions are well known and see if I can ...
1
vote
0answers
23 views

Dealing with stochastic results of Machine Learning Models

I'm building stock selection models, and pick top 5 and bottom 5 stocks. Given the variability in Stochastic gradient decent results, they keep changing. One way to get consistent results is to use ...
0
votes
0answers
16 views

What is the correct order of operations when cleaning and structuring financial time series?

I'm studying Lopez' Advances in Financial Machine Learning where he talks about how to sample and structure financial data, as well as how to apply machine learning models to the data. I am also ...
-3
votes
0answers
19 views

how to take fold difference? [closed]

![Remove from train data genes with fold differences across samples less than 2. Fold difference is defined as a ratio between maximum and minimum values (Max/Min) for a given data set.]1
5
votes
0answers
59 views

What machine learning algorithms are important for quant interviews? [closed]

I'm not sure if this question is appropriate for this SE board. If not, I can definitely remove it. FWIW, I saw a few other interview-related questions posted on here. Anyways, I will be ...
3
votes
1answer
107 views

Forecasting volatility with machine learning: Performance comparison

ARIMA and GARCH are old news for predicting volatility time series of asset returns. How does the performances of machine learning algorithms compare (such as random forest, support vector ...
1
vote
1answer
54 views

What's the meaning of linearity in classical statistics in Prado's book?

I am reading Prado's new book, Machine Learning for Asset Managers. In the page1 of his book, there is this sentence. To a greater extent than other mathematical disciplines, statistics is a ...
0
votes
1answer
50 views

How can I combine traditional trading patterns and machine learning algorithms to produce a trading system?

Traditionally, retail traders have leveraged on price patterns discovered by applying graphical tools such as flags, fractals, pennants, heads, shoulders, etc. However, while this method has been ...
2
votes
0answers
36 views

What benefits do using log returns for model training provide?

I came across a paper that uses Support Vector Machines to classify a buy/sell/hold decision each hour at the $\pm$0.5% threshold. The paper can bee seen here. The ...
0
votes
0answers
23 views

Machine-learning (python) non-parametric continuous variables and output

There are various machine-learning techniques available, of which I know there is the (K) NN -> nearest neighbour. However, it seems most non-parametric ML techniques need the input and output to be '...
1
vote
1answer
24 views

Mutual fund rating predictions

I am working on a dataset with aim to predict the MF ratings. There are cols like, 10 yr, 7 yr, 5 yr etc returns. I also have commencement date of MFs, the question is there are MFs with commencements ...
11
votes
4answers
5k views

Is it really possible to create a robust algorithmic trading strategy for intraday trading?

I'm an engineer doing academic research for my master thesis in the area of quantitative finance, basically the purpose is to study the possibility to create an intraday-trading algorithm. I've tried ...
3
votes
2answers
93 views

Does the non-causal nature of quant models limit their applicability?

I understand that to describe financial data, we build stochastic models and calibrate their parameters to past data. When coming up with new algorithms, we rely on rigorous backtesting to convince ...
1
vote
0answers
20 views

How to use multi-periods and mult-factors to predict stock price by linear regression?

Give data in $t_n$ denoted by $[x_1^n, x_2^n, ... x_d^n]$ and label $y_n$ to be predicted. We can just train a $d$-dimensional linear regression $y_n=\sum b_ix_i^n$ to make a prediction. However, I ...
2
votes
0answers
73 views

Meta Labeling for trading opportunities

In Advances in Financial Machine Learning, Lopez explains how we should build a primary exogenous model (binary classifier) to identify trading opportunities and a secondary meta model to filter out ...
4
votes
4answers
249 views

Backtest overfitting - in-sample vs out-of-sample

Recently, I read a great paper by De Prado et al. on backtest overfitting problem in Quantitative Finance titled Pseudo-Mathematics and Financial Charlatanism: the Effects of Backtest Overfitting on ...
1
vote
1answer
63 views

Appropriate Encoding for Stock Technical Indicators ? RSI

happy new year and i am new to machine learning + python.. so recently i am doing a project on my own to use machine learning models on technical indicators.. I have my technical indicators data ...
0
votes
1answer
134 views

Why meta-labeling is is robust?

With all due respect, I saw this technique in the book , Advances in financial machine learning, but I found that it acts like a filter for the trades only. And it seems doing the job of overfitting ...
4
votes
1answer
268 views

The “Universal Model” by Justin Sirignano and Rama Cont

In the nicely written article https://arxiv.org/abs/1803.06917 by Justin Sirignano and Rama Cont, they explained that their model is universal and stationary. I am a bit confused about some questions. ...
0
votes
1answer
79 views

Sample uniqueness and sample weight in AFML book

With reference to AFML ("Advances in Financial Machine Learning" book by Marcos Lopez de Prado). Are sample uniqueness and sample weight pointing towards to the same thing? I am confused on the term ...
1
vote
1answer
207 views

How can I approximate Dollar Bars from Minute Data instead of Tick Data?

Having been influenced by de Prado's Advances in Machine learning book, I've set out to build the dollar bars (in which each bar represents a set dollar amount of transactions in the security) that he ...
5
votes
1answer
209 views

How to use neural network for technical analysis?

I am working on building a Neural network for technical analysis of stocks. The input I have is the open price and two (so far) technical indicators : RSI and William's R - for the past 2 years. I can ...
3
votes
1answer
97 views

Dollar bars in Advances in Financial Machine Learning book

Does anyone have use the dollar bars for building a strategy? I would like to know what ways you guys might be interested to set the dollar bars' parameter ( the dollar value ). I have thought of one ...
0
votes
1answer
93 views

Random Forest on financial time-serie?

Is it okay to apply Random Forest to a non-stationary financial serie? Or would it be correct to first difference the serie and then apply Random Forest to the new serie?
1
vote
3answers
239 views

What's a good resource of book for Python programming in relation to quantitative finance?

I know some of base Python, but I have only briefly used numpy, pandas, etc... I was wondering what's a good resource to learn Python specifically for quantitative finance. I know of plenty of books/...
2
votes
2answers
148 views

Flexible horizon in Triple Barrier Method

I'm going through "Advances in Financial ML" book and I really like the ideas behind Triple Barrier Method and using a flexible horizontal threshold based on volatility. What bothers me is that an ...
1
vote
0answers
61 views

Using news to predict Stock Prices dataset

In order to build Regression or Deep Learning models for predicting the market, we need a bunch of historical data. Prices and technical indicators are easily accessible, but getting news from the ...
132
votes
15answers
167k views

How can I go about applying machine learning algorithms to stock markets?

I am not very sure, if this question fits in here. I have recently begun, reading and learning about machine learning. Can someone throw some light onto how to go about it or rather can anyone share ...
1
vote
0answers
158 views

Machine learning for portfolio optimization

What algorithms from machine learning, supervised learning or unsupervised learning have been recently used for asset allocation models as alternatives to the Markowitz mean-variance optimization ...
2
votes
0answers
57 views

machine-learning method to predict PCA weights

I have been using certain linear-regression to extract the PCA (top 3) weights relating to a certain data-set. I was wondering, instead of using linear-regression to generate the weights, I can use ...
2
votes
1answer
66 views

Labeling and excluding specific market conditions

I'm going through "Advances in Financial ML" book and got stuck with something which is not covered there (correct me if I'm wrong). Let's assume I labeled data to 0, 1, 2 according to triple barrier ...
0
votes
0answers
33 views

Clusters evolution over time

I have a dataset of stock prices and I want to group stocks that share similar characteristics together using cluster analysis. I'm interested in following the evolution of each cluster over time, but ...
2
votes
1answer
95 views

Choosing best expressions from all possible combinations on variables, unary operators and binary operators along with hyper parameters

I have a few financial variables of a stock universe like OHLC prices, volume, and other fundamentals with varying time-frequency. Using this set I'm creating an expression that gives the weights to ...
1
vote
4answers
2k views

What Is A Good Success Rate Using Machine Learning For A Beginner?

I know this question will be quickly destroyed and my account summarily banned, but I just have to ask: For a trader using machine-learning algorithms (SVMs, ANNs, GAs, Decision Trees) for ...
2
votes
2answers
159 views

When to stop training?

I have built a deep reinforcement learning based portfolio optimisation agent. At a high level it is using macro economic data, valuations of the assets and a few technical indicators as the features. ...
2
votes
0answers
48 views

Conceptual help - Machine Learning on finance data set [closed]

I am working on Anomaly detection model problem for a finance data set - set of gift card activation transactions. My team member suggested an idea that " First train the model with normal instances ...
2
votes
1answer
125 views

Building a semi-discretionary system

I've been investing for the last 15 years in a weird Buffett/Soros way. For the last few years I've been toying with the idea of modeling myself. I want to build a 'stock screener' that will be able ...
1
vote
1answer
77 views

Random Forests - Trees vs Predictors

This question relates to the use of random forests in finance and the relationship between the number of features, the observations, and the number of trees. Consider the relation between an RF, the ...
3
votes
3answers
210 views

Getting sets of random correlated variables

For the training of a machine learning model I need to add additional features (macro variables), and these features are correlated. I need to run the model N times, and for each time I have to add ...
1
vote
1answer
94 views

Modeling mortgage loan defaults

I have a machine learning model trained with a list of mortgage features that include macro variables where the field to predict (the label) is "Mortgage Defaulted" = 1 or 0 (Yes or No). Now, I need ...
1
vote
1answer
151 views

How can stationary time series data be used as input in an ML model?

I am halfway through "Advances in Financial Machine Learning" by Marcos Lopez de Prado. I understand that a time series like stock prices can be transformed to make it sufficiently stationary. ...
1
vote
1answer
205 views

Which machine learning model rely on the normality assumption?

In the machine learning project, when the target variable is skewed, we need to use box-cox transformation to turn that into a normal distribution. But why do we need to do that? I mean, besides the ...
2
votes
1answer
141 views

Calculating PD of commercial bank loan

I have two main options to calculate PD of a loan in a commercial bank; with and without machine learning. On one hand, there are traditional methods such as Merton or KVM. On the other hand, I could ...
1
vote
1answer
86 views

Combine fundamental and market data into one ML model

What are the best tested ways to preprocess data with very different frequencies such as fundamental and market data into same ML model for quant trading?
1
vote
2answers
98 views

Lower MSE results in less profit when using Machine Learning

When using Machine Learning for predicting stocks, can a lower Mean Squared Error result in less profit after Backtesting or is there a mistake in the experiment?
36
votes
4answers
9k views

What types of neural networks are most appropriate for trading?

What types of neural networks are most appropriate for forecasting returns? Can neural networks be the basis for a high-frequency trading strategy? Types of neural networks include: Radial Basis ...
2
votes
0answers
355 views

Information Driven Bars (Advances in Financial Machine Learning)

My team and I are busy coding up a python implementation of the information driven bars (imbalance and run bars) mentioned in Chapter 2 of the text book Advances in Financial Machine Learning. There ...
6
votes
1answer
578 views

What machine learning method is more suitable for prediction of financial time series?

I have time series data for various assets and which I transform to create various features. I have framed the problem as a classification task where I attempt to predict either a positive or negative ...
8
votes
2answers
313 views

Defining an objective function for machine learning task of trading

A simplified example. Given: asset's price time series fixed distances to stop and target. A function of these inputs has two possible output values: $1$ if price is likely to hit the target ...