The tag has no wiki summary.

learn more… | top users | synonyms

47
votes
10answers
30k 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 ...
18
votes
4answers
2k views

Any research on how natural language processing can be used to forecast stocks?

Is there any published research of decent quality linking news or unstructured information to asset returns? I know that Thomson Reuters offers its Machine Readable news (MRN), so somebody must use ...
11
votes
3answers
2k views

How to incorporate technical indicators into neural networks?

I plan to develop a neural network to trade commodities futures, but while messing around with some code, a question came up. If I understand correctly, people use various technical indicators with ...
10
votes
4answers
4k views

Using linear regression on (lagged) returns of one stock to predict returns of another

Suppose I want to build a linear regression to see if returns of one stock can predict returns of another. For example, let's say I want to see if the VIX return on day X is predictive of the S&P ...
8
votes
1answer
2k views

Multilayer Perceptron (Neural Network) for Time Series Prediction

I have it in mind to build a Multilayer Perceptron for predicting financial time series. I understand the algorithm concepts (linear combiner, activation function, etc). But while trying to build the ...
6
votes
10answers
2k views

Using Black-Scholes equations to “buy” stocks

From what I understand, Black-Scholes equation in finance is used to price options which are a contract between a potential buyer and a seller. Can I use this mathematical framework to "buy" a stock? ...
6
votes
2answers
375 views

The T+H Problem in Factor model forecasts

Suppose we train on M individuals consisting of T observations (i.e. TxM design matrix). The dependent variable is one-year return for each security (H = horizon of one year). In a factor model ...
5
votes
5answers
2k views

How many explanatory variables is too many?

When researching any sort of predictive model, whether using ordinary linear regression or more sophisticated methods such as neural networks or classification and regression trees, there seems to ...
5
votes
1answer
239 views

Quant teams predicting the World Cup

It is a good tradition of the quant teams of the major banks to predict the World Cup. As an example see this new paper from Goldman Sachs: The World Cup and Economics 2014 (Brazil will win by the ...
5
votes
0answers
746 views

Tools/R code for predicting Dragon-Kings

The theory of the so called Dragon-Kings, esp. by Didier Sornette (ETH Zürich), basically states that financial crises and crashes are predictable (contrary to the theory of black swans). The ...
4
votes
2answers
397 views

Predict Market Direction, What is forecastable/unforecastable?

Let's decompose the return process $R_t$ as follows : $$R_{t} = sign(R_{t}) * |R_{t}| $$ What's part of the equation is forecastable?
4
votes
0answers
460 views

Algorithms for predicting a couple points in the future

I'm familiar with supervised learning algorithms like regression and neural networks which look at a bunch of input points and learn a function which outputs a value (the value varying depending on ...
3
votes
3answers
244 views

Implementing A 50/50 Prediction Model Strategy

Reworded the question for clarity (see edits for original post): How can one knowingly foresee where a 50/50 prediction model will be profitable? For previous posts: I understand that if I have a ...
2
votes
0answers
138 views

Good criteria to sort state-space $\beta_{t}$ according to Kalman filter output

Let the usual state-space linear model (without constant term for the sake of simplicity): $y_{t}=\beta_{t} X_{t}+\epsilon_{t}$ If we use Gaussian Kalman filter to estimate $\beta_{t}$ we get ...
1
vote
1answer
332 views

GARCH model and prediction

I have a question about the prediction of volatility and returns of a time series. Basically it is a question about prediction in the ...
1
vote
1answer
90 views

Economic indicators leading the yield curve

There is a lot of research on how the government yield curve can be used to predict the economy. The government yield curve is often seen as a leading indicator. But for which variables is the curve a ...
1
vote
0answers
60 views

How to choose a window for curve fitting and prediction?

I am using Pareto distribution to fit a serie of survival rates (with least square). My ultimate goal is to use this fitting curve for prediction. Thus I would mainly focus on the tail of the ...
1
vote
0answers
456 views

Oscillatory time-series forecasting

I was wondering if this mean(160)-reverting/oscillatory time series "SUM" can be considered chaotic & forecastable to some extend short-term? ...
0
votes
1answer
458 views

Which prediction market model is efficient and simple to use?

For a college project I'm tasked with implementing prediction market. Which model of it I'd better choose? I want something useful and simple enough for other people to quickly understand and use. ...
0
votes
1answer
363 views

Selecting timeframe for time series analysis

In technical analysis, we may use confluence of direction for 3 timeframes to roughly gauge bias of market now. Similarly, if we use time series forecasting methods to predict(say daily data-whether ...
0
votes
2answers
284 views

Howto Calculate An Error's Partial Derivative in ANN

This is a follow-on question from this post I made, "Multilayer Perceptron (Neural Network) for Time Series Prediction", a few months back. I'm constructing a feed-forward artificial neural network, ...
0
votes
0answers
26 views

Obtaining historical data of individual level predictions from prediction markets

I have been searching the internet but was unable to find data of the following form: prediction of events for which we already know the outcome (i.e. markets that have already closed) data for each ...