All Questions
234 questions
0
votes
1
answer
92
views
CNN-1D for time-series data returns strange accuracy [closed]
I am using keras to train a 1D CNN with time-series as input data to perform a binary classification. The model part of the code is the following:
modelo = Sequential()
modelo.add(Conv1D(filters=32, ...
- 171
0
votes
0
answers
31
views
Attention masks on time series data with keras funktional API
Im currently trying to study the effects of masking attention on a transformer model trained to classify time series data. My model works so far and give me okish performance, but when i try to mask ...
- 31
-1
votes
1
answer
63
views
Why does this simple machine learning code give the wrong answer?
I'm trying to learn some time-series neural network ML and was getting weird solutions, so I'm trying to model the simplest non-trivial case I can think of, which is predicting n+1 as the next number ...
- 1
0
votes
0
answers
69
views
Keras LSTM model and predicting beyond validation set
I am currently encountering issues with formulating a prediction beyond my validation set. When utilizing a validation set, my model works fine and I am able to achieve a credible prediction.
However, ...
0
votes
0
answers
45
views
Why do my LSTM multi-step forecasts explode, despite low MAPE on validation set (single-step) on very simple linear trend?
Example below is self-complete.
I have recently switched from using darts (where forecast horizons etc) are all handled for me to keras because I wanted to integrate with other libraries such as shap ...
- 29
0
votes
0
answers
41
views
LSTM forecasting horizontal line with standardized datas
I’ve seen many topics about the problem I have in my situation but nothing help.
I am trying to make a forecast on a stock price with a Bidirectional LSTM.
My problem here is that the forecast on test ...
- 417
-1
votes
1
answer
291
views
Why my LSTM Model forecasts almost straight line on validation set?
I trained a BI-LSTM model on stock prices.
For this model, I did 2 approaches of backtesting :
Applying the predict function for the whole validation set and then compare predictions to real data
...
- 417
1
vote
1
answer
47
views
Understanding the input_shape of LSTM model
I divided my database in 40 rolling windows so I have a dataframe with shape (2000000, 132). Let's concentrate in the first window: it has 50k rows and the 132 columns so its shape is (50000, 132). I ...
- 13
0
votes
1
answer
448
views
Adding attention to seq2seq LSTM Model
I'm trying to make a time series prediction project for stock prediction that also displays feature weights (as in, what aspects of the data were most important - i.e. closing price, volume, technical ...
- 51
1
vote
1
answer
67
views
Forecasting Multivariate Time Series (in chapter 15 of the book "Hands-On Machine Learning...) Error
I am working with the Jupyter Notebook of chapter 15 of the Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow book by Aurélien Géron (Third Edition). I encountered an error in cell ...
0
votes
0
answers
115
views
I get KeyError for model.fit() fed with timeseries data
I am building an LSTM model for which I want to prepare my time series data with TimeseriesGenerator. I attached an image of the output of the TimeseriesGenerator, which is a sequence object.
enter ...
0
votes
0
answers
59
views
Why is the prediction length longer than expected with this LSTM model?
I'm working on a multivariate time series forecasting problem where I have 2 features and 15 time steps and I want to predict one/two future values. My data set shapes are as follows:
Training Shape: (...
1
vote
1
answer
1k
views
(EMpirical Mode Decomposition+CNN) for time series forecasting
I'm currently working on a time series project, and I intend to employ the EMD+CNN technique for forecasting the output. Upon applying EMD to the training data, I obtained a total of 14 Intrinsic Mode ...
- 11
0
votes
2
answers
94
views
Neural Network Architecture for Time Series as Inputs and Outputs with Variable-Length Inputs
I'm currently learning and working on implementing a time series prediction using different packages TensorFlow, Pytorch Neural Network. My goal is to feed a combination of time series data (GM Data) ...
- 3
1
vote
1
answer
73
views
Predicting new timeseries based on related timeseries?
Let's say I have multiple timeseries, representing different features, all of length n, and I want to predict a new timeseries which represents another feature, without any past history for that ...
- 623