Questions tagged [time-series]
Time series are data observed over time (either in continuous time or at discrete time periods).
1,820
questions
0
votes
0
answers
7
views
loss: NaN when training ucr timeseries set
I'm trying to change the input of this model,
https://keras.io/examples/timeseries/timeseries_classification_from_scratch/
the model architecture is as follow:
...
1
vote
1
answer
31
views
Best ML models for long term time series forecast
I have a project to make a long term prediction (like 5 years) of electricity production by types of power plants (solor, wind, coal, nuclear etc.).
I have access to time series data in MW [megawatts] ...
1
vote
0
answers
23
views
Mining association rules between time series
I have a pandas dataframe that represents a time series. My time series is segmented over the phase type that the robot is performing (i.e. I have a column with the phase type per timestamp and the ...
0
votes
2
answers
20
views
Using time serie to predict another variable
I would like to analyse head rotation data in space. For this I measured at 15HZ the rotation around the X, Y and Z angles for a little more than ten minutes. I would like to use these movements to ...
0
votes
0
answers
36
views
Bugs in the backpropagation algorithm in Python
I've been trying to create a simple Neural Network from scratch with a backpropagation algorithm to predict the next number based on 3 previous numbers. But for some reasons, MSE(Mean Squared Error) ...
0
votes
1
answer
13
views
Stratifed time series split with the same imbalance ratio
I am recently working on an imbalanced binary classification problem where the data is time ordered. I would like to validate my model using training/validation splits that have the same imbalance ...
0
votes
0
answers
9
views
Problem formulation of future timeframe prediction based on current time
I have a problem where I want to predict "when is the next action happening" based on the time.
Example problem: Imagine you have a dataset of transactions per user, your goal is to predict ...
0
votes
0
answers
15
views
time series differencing and prediction with the differenced data
I am using ARIMA for some time series models and some of them were not stationary and needed differencing. So then I used the differenced data for the model. I also split it for training and testing:
<...
0
votes
1
answer
32
views
Patterns extraction in time serie with DTW
I have a long time serie, let's say 1000 items. I want to find patterns in it of different lengths from 10 to 100 elements.
To do this, I extract sliding windows of different lengths and calculate ...
0
votes
0
answers
13
views
Multivariate time series - predicting value on multiple correlated variables
I have a dataset of the following structure:
daily sales data for the last 5 years
monthly economic trends (there is actually more)
The objective is to forecast sales on daily & monthly level ...
0
votes
1
answer
31
views
Is it cheating to use normal KFold for data that is collected over time?
I am in doubt when to use strict time-series cross validation and when to use kfold. I have the following situation, which, I believe, is an edge-case between time series and normal data:
I have a ...
0
votes
1
answer
26
views
Combine machine learning feature selection with time series
I have basic knowledge in time series prediction and supervised/unsupervised machine learning algorithms (clustering, classification, decision tree, etc.) I am now given a task to predict a bunch of ...
0
votes
0
answers
14
views
Framing a probabilistic time dependent problem
I need help framing the following problem:
I have a dataset where I know for each day, at customer level, that someone with device X bought device Y.
Example:
At day 1
50 people with device X bought ...
0
votes
0
answers
18
views
Probability of a Maximum in a Time Series Given Past Data
I'm trying to predict the peak power usage of an EV charging station. I would like figure out probability bounds given the peak power throughout the month.
Imagine that our EV time series consists of ...
0
votes
0
answers
3
views
R - Using XTS objects: newdata has X rows but variables have X rows
My observations come from an xts object, which is indexed to a time, the same as my newdata?
Where X is a xts object indexed to dates from 01-01-2002 to 01-12-2022 including 26 variables
...
0
votes
0
answers
9
views
Treat multiple periods of huge outliers in time series data with weekly seasonality data
How can I model a time series data (average sales is around 20K) with weekly seasonality that has multiple recurring outlier periods for example 4 days of huge volumes (around 150K) in March and 14 ...
0
votes
1
answer
22
views
What is exactly the input to a second lstm layer?
I am often confused about the lstm with more than one layer.
Imagine i have two lstm layer with 3 cells each layer.
What is exactly the input to the second lstm layer ?
0
votes
0
answers
5
views
How to learn from a set of $N$ independent time series physical experiments?
Suppose that I want to learn the lift force that a flapping wing generates over time, given that the wing flaps with some predefined profile. To do so, one might conduct a set of $N$ experiments, each ...
0
votes
0
answers
39
views
Time series Classifiction - is LSTM better than XGBoost
My question is whether LSTM RNN is a better predictor of an label (note not forecaster) than XGBoost. Thus far I have had moderate success with XGB but I wonder if the tree nature, random start and ...
0
votes
0
answers
9
views
How to calibrate autoregressive model?
TL;DR What metric, and how to calibrate autoregressive language (deep learning) model?
Background
Usually there are several popular approach to calibrate a non-autoregressive model such as isotonic ...
0
votes
0
answers
21
views
Which algorithms are suitable for time series classification for this form of data?
Newbie here, I have a large list of csv files that contain a series of probability distributions (for 5 classes). I'm trying to train a binary classifier that classifies each file into either a ...
0
votes
0
answers
15
views
Covariance of forecasts from Python/statsmodels SARIMAXResults object
I have a SARIMAX model fitted at daily frequency using statsmodels.tsa.statepsace.sarimax. It is a "full" SARIMAX model in the sense that it has AR, MA, ...
0
votes
0
answers
11
views
Many To One LSTM - Can I Use the Same Sequence as Input from Previous Timesteps?
I'm new to LSTMs, and I'm trying to do a basic timeseries prediction using stock prices. However, I'm a bit confused as to how the LSTM is supposed to remember outputs from previous timesteps when it ...
-1
votes
1
answer
16
views
Time series forecast where variable depends on another variable which is time dependent
I am currently making a weather forecast prediction using time series and have that temperature depends on the time of the year and can make models using this, however it also has dependence on ...
0
votes
0
answers
17
views
Time series forecasting: Youtube Views
I have some monthly data for 200~ videos from a youtube channel. I can see how many views each video got each month. Videos were released consistently each week and there is no missing data.
Usually a ...
0
votes
1
answer
28
views
time series forecasting with two columns
I have a task which is time series forecasting with two columns
to predict Number_of column. so I wonder what is the approach to deal with these two time series to predict Number_of column.
0
votes
0
answers
14
views
Can Pybats' Analysis function make a prediction on a future DateTime object that is only one step beyond the final point of the existing data?
I was able to utilize the Bayesian approach of statistics in Pybats in order to make a forecast model on a timeseries dataset. While the model is learning from the ...
0
votes
1
answer
12
views
Time series convert/summarise series of values into a single value
Hi I have a time series dataset which looks like this
Date Value1
2021/08/01 2
and
...
0
votes
1
answer
17
views
Theory behind time Series Test dataset being the last x%
The standard flow for time-series that i'm aware of, is that you divide your dataset for Training & Validation (60% and 20% respectively for example) and the last 20% is used for Unbiased Testing....
0
votes
0
answers
18
views
Time series decomposition: Magnitude of result really high
Im using statsmodels mstl to decompose time series data. Results are shown below.
The trend signal, to some extent makes sense with respect to how it is changing its peaks and so on. But I cant ...
0
votes
0
answers
9
views
finite difference vs difference quotient for temporal features
Let's say I have daily snapshots for some feature f, e.g., daily event counters. Now I want to add a second order feature g that tracks how f changes over time.
This can be done in several ways, but I'...
1
vote
1
answer
28
views
Best way to detect newly incoming anomalies in two timeseries?
I have two devices that both send data (let's say temperature). I need to be able to detect if one of the devices reports an unusual/anomalous reading. The case if both of the devices report a "...
0
votes
1
answer
14
views
General methods to deal with time series data
Sorry I'm new to machine learning and statistics.
For time series predictions, do you use RNN or something? For example, the past 2 years' sales of a product.
TBH Im pretty much unfamiliar with how ...
0
votes
0
answers
12
views
Is it normal for a SARIMA model to produce no residuals?
I'm working on my first time series project where I am required to produce predictions for financial data.
The raw data is below:
Clearly, there is a seasonality and downward trend, I used the ...
0
votes
0
answers
12
views
Relative changes instead absolute values in LSTM training
I am reading some papers about glucose time series prediction and I have noticed that some of them propose LSTM models that use relative changes between two measures.
For example, if $$ glucose(t)=60, ...
0
votes
1
answer
29
views
Forecasting on multiple timeseries data with limited data points
I'm predicting operational expense of a stores of a company. I have only six years of data per store at a daily granularity. I want to train a model to predict the next years operational expense. In ...
2
votes
1
answer
37
views
Early anomaly detection / Failure prediction on time series
My problem here is that I want to predict failures in advance with respect to their occurrence. I have sensors mounted on my machine and with a certain frequency, they send data to my database. ...
0
votes
0
answers
4
views
ExponentialSmoothing holtwinters with Keras Interace
Is it possible to wrap the statsmodels holtwinters with the Subclassing API in keras?
The reason i want to do it, is i have a WindowGeneratorthat creates me batches ...
0
votes
0
answers
8
views
Is this GRU learning good?
Result seems to be a little out of "expected" values.
It's timeseries dataset.
0
votes
0
answers
28
views
How to handle multiple multivariate timeseries?
I am trying to develop a model using machine learning that reproduces a biological behavior. My goal is to do a regression of timeseries e.g from multiple input each time_step predict multiple output :...
0
votes
0
answers
19
views
Can neural network be able to convert analog timeseries to discrete timeseries
I have timeseries signal of sound echo back from instruments. They are firing kick, marker, wall, echo noise.
Since neural network can produce Seq2Seq prediction. I am using ResNet + 1DCNN to produce ...
0
votes
0
answers
13
views
Tensorflow prediction of (PRNG) future values
I would appreciate if you could help me with the following problem:
Future values of a given time series of pseudo-random values should be predicted. It is unclear how good the PRNG performs and if it ...
2
votes
2
answers
85
views
Timeseries (InfluxDB): How to deal with missing data?
Question Description
We are performing a lot of timeseries queries, these queries sometimes result in issues, they are usually performed through an API (Python) and sometimes result in complete ...
0
votes
0
answers
18
views
General approach for "regime detection" within timeseries data
Assume a stock market type of dataset with a handful of timeseries, representing volume of trades, volatility of trades, and similar meta metrics. If necessary, assume that is on an hourly basis.
What ...
0
votes
0
answers
13
views
How to make a predictive model using a timeseries data consisted of binary information?
I have a set of data that is showing the state of an object as a function of time. I would like to know what and how I should be utilizing machine learning to predict the state of the object at some ...
0
votes
0
answers
18
views
Transformer doesn't generalize on a time-series data
Data
120 patients.
Each patient has 5.7556e+06 samples on average, each sample consists of 5 features stored as a continuous high-frequency (1000Hz) time series.
Labels are 13 discrete classes ...
0
votes
0
answers
24
views
How to do forecasting with categorical timeseries?
I have a dataset that is in the form of categorical timeseries: (specifically, we either know or don't know the values of 6 degrees of freedom of an object at any given time). If we know it, it's ...
0
votes
0
answers
7
views
References to online service/platform dedicated to "time series prediction"
Do you have any references to online service/platform dedicated to "time series prediction" ?
For one product under development, we need to perform frequent (i.e. one per 15 minutes) ...
0
votes
0
answers
16
views
What are some methods to convert time series data into images for CNN?
I am working on a project where I have specific time series data which I would like to convert to images. I have investigated various methods, such as Markov Transition Fields, Gramian Angular Fields, ...
1
vote
1
answer
17
views
ANN time series classification validation loss never decreases
Problem statement: E2E classifier
Input: [7x3600] time series of physiological parameters recorded from a medical device.
Output: I am trying to learn a binary classifier to determine if the device is ...