All Questions
Tagged with online-algorithms time-series
14 questions with no upvoted or accepted answers
5
votes
0
answers
234
views
Detecting trends in a data stream in real-time
I'm trying to detect trending topics on Twitter in real-time. What I'm doing is every time I get a tweet I assign the tweet to the cluster that talks about the same topic as the tweet. Regardless of ...
- 8,411
5
votes
0
answers
532
views
Reference for implementing generalized likelihood ratio test to determine online whether time-series mean has shifted
What is a reference that describes the "generalized likelihood ratio" test to determine online (i.e., meaning that we add an observation, then check, then add an observation, then check) whether the ...
4
votes
0
answers
362
views
Continuous time series classification with lstm in Keras?
I have been researching time series classification with LSTM. I've seen examples where they provide continuous predictions, i.e. the prediction is updated at each time step. Is it possible to train a ...
- 1,239
2
votes
0
answers
313
views
Adjust decay rate dynamically
Say I have a stream of values $\langle s_1, s_2,\ldots\rangle$ coming in and a function
$$E_{s_1:s_n}(t) = E_{s_1:s_{n-1}}(t-1) + \alpha\cdot (s_t-E_{s_1:s_{n-1}}(t-1))$$
that compute their ...
- 121
2
votes
0
answers
319
views
Forecasting multivariate time series data stream
I have a multivariate time series data stream. I am looking for a method that can forecast the next value of one of the variables as the data comes in. (It would be a major advantage if there's an R ...
- 149
1
vote
0
answers
71
views
Improve HMM state estimation in latest data
I have a time-series dataset that is poisson-distributed, where each day I get a new additional datapoint. If I input all the data into a HMM (I am using code I found from hmmlearn in python) it does ...
- 91
1
vote
0
answers
44
views
Which metrics should be used in preprocessing in continual learning?
So my idea is to train an LSTM - autoencoder for anomaly detection by continual learning, i.e., I want to update the model after each 10 time steps. Firstly I will train it on source data, then re-...
- 753
1
vote
0
answers
35
views
Online estimation of drifting discrete probability
I recently come across (in a practical setting) to the following problem. Suppose I receive items from a finite set ,one at a time . At each moment one item is drawn independently from an unknown ...
- 201
1
vote
0
answers
236
views
Online deseasonalization of time series data
Are there any existing methodologies of deseasonalizing time series data online, in order to avoid lookahead bias? It seems that if you don't deaseasonalize time series data online, you would not be ...
- 159
1
vote
0
answers
47
views
Predicting user selections based on previous answers and datetime
I'm completely new to machine learning and wish to implement it into my app to help my users travel between places. Let's say I have data (constantly updating data) that looks like this:
...
- 111
1
vote
1
answer
56
views
A way to estimate if a random variable has shifted beyond a threshold
I have a random variable estimated over time by an online algorithm. I have the mean and variance of the random Gaussian variable at every step t. I expect the time series to have sudden shifts. What ...
- 11
0
votes
1
answer
130
views
Time series model in production - Re-train on the fly as as batch process?
Let's say I've a time series of phone calls per day over the last three years. I could train a model using exponential smoothing (e.g. HoltWinters) for predicting the future amount of phone calls per ...
0
votes
1
answer
94
views
Classification of Imbalanced and Streaming Time Series Data
I have a question about classification of time series. Data has two features and I want to classify it into 5 classes. We have a stream of data and new data is generated every 5 seconds. Moreover in ...
- 1
0
votes
0
answers
38
views
What are some major theories on picking the right number for the sample window size in time series analysis?
for example the number of samples to run the moving average, or the number of samples for sequential hypothesis testing. Or if there is a control scheme going on what is the best time window for an ...
- 167