Questions tagged [forecasting]
Prediction of the future events. It is a special case of [prediction], in the context of [time-series].
3,644
questions
0
votes
0
answers
14
views
Incorporate partial information about Y into predictions
I have a linear regression model predicting exports of toys from the United States on an annual basis. This initial model is based on a few factors: toy companies' demand projections, toy production ...
- 11
6
votes
2
answers
30
views
Who estimated war casualties from tightly-controlled government news sources?
I've read about this historical case before so I thought it would be very easy to Google, but after a few dozen queries that come up with nothing relevant I'm ready to punt.
The story goes like this. ...
- 301
1
vote
0
answers
20
views
Update to Box and Jenkins Air Passenger data? [closed]
A textbook example of a time series is the Box and Jenkins Air Passenger data. In R you can get it with the command data(AirPassengers). It has the number of ...
- 257
0
votes
0
answers
26
views
How can I predict a 2D array over time?
I've got a rectangular region that's composed of 1024 grid cells (32x32 cells). Each of these cells has an associated value, which then builds me a 2D array.
For that 2D array, I've got 8 samples (...
- 101
0
votes
0
answers
4
views
Optimization of Loss Function of Multivariate Forecasts
I am trying to write an optimisation function in R for the following problem, which aims to estimate the weights for a combination forecast based on the loss for the in-sample period $t = 1,...,T$.
$\...
- 111
0
votes
0
answers
14
views
Negative data for log transformation [duplicate]
I am analysing data on hourly electricity prices to try to do some forecasting, in my dataset I have mostly positive values, but some negative, around 20 per region for the two year duration. I want ...
0
votes
0
answers
16
views
Forecasting at very granular level (sparse data) - how to aggregate or disaggregate? [closed]
I am trying to forecast the number of orders of laptops, which can have different combinations of features, like with x Ram, y color, z CPU, 13inc, etc, at the week level.
And for this, I have my ...
- 1
1
vote
1
answer
52
views
Poor auto-ARIMA predictions
I am trying to fit and forecast water production in a well and this accounts for my end of training thesis. But I got poor prediction from ARIMA and sarima models. I tried with auto ARIMA but it didn'...
- 13
1
vote
0
answers
13
views
hard negative mining equivalent for prediction/forecasting problems
Input: past history 3D velocity components of an object up to time t; history size is w (window or lag) seconds in the past.
Output: predicted future possible velocities for times in the range t < ...
- 11
0
votes
0
answers
66
views
Predict user's next login time
I am trying to implement a model to predict the next time a user will login to some system. The only data I have is the user ID and the login time.
The distribution for the time between each users' ...
- 1
1
vote
1
answer
27
views
Deal with quarterly or monthly seasonality in forecasting a year ahead
Assume a time series with a clear seasonality with observations every quarter. If you want to use that time series and make predictions four steps ahead, but you are only interested in what the ...
- 137
0
votes
0
answers
23
views
Global forecasting with Random Forests
The global approach for forecasting a group of time series involves training a single univariate model across all series, see Montero-Manso and Hyndman. Regression trees, e.g., Random Forests, perform ...
0
votes
0
answers
21
views
how to use GAMs for seasonal time series forecasting m
I have a daily time series with multiplicative seasonalities : yearly, monthly and weekly seasonalities.
I want to try a GAM model to forecast the time series
I don’t know how the trend should be ...
- 1
0
votes
0
answers
11
views
Forecasting Methods for "In Progress" Systems?
I'm working on stats/analytics for a logistics system. Projects materialize, go through a complex multi-step sequential system (can take weeks/months), and are finally realized as revenue after ...
- 11
2
votes
1
answer
36
views
Computing reconciled prediction intervals when forecasting logged outcome variable using fable
EDIT: Is seems like the dev version of fabletools (.3.2.9000) includes the capability to do what I want via the boostrap option. I'm leaving this question unanswered until things get formally released....
- 35
0
votes
1
answer
17
views
Difference between seasonality-adjusted data and the trend component
After decomposing the time series, what is the intuitive difference between seasonality-adjusted data and the trend component (from decomposition)?
- 5
1
vote
1
answer
33
views
AR And MA Order
I have a time series which has sequence as follows
Upon eye balling this series , it sounds me a series which has 20 cycles where frequency/counts of event increase from 0 and then decrease after ...
- 63
0
votes
0
answers
35
views
How to interpret ACF and PACF in time series?
In this following monthly sales time series, how can I interpret ACF and PACF?
STL Decomposition
ACF:
PACF:
- 5
1
vote
0
answers
10
views
Intermittent Demand Forecasting for highly seasonal items
I have a dataset with intermittent sales and very high seasonality and I want to forecast that but it is my understanding that Croston's method only works on non seasonal items. Is there any other ...
0
votes
0
answers
14
views
Forecasting two dependent count variables using single independent variable (Time)
I'm stuck with a modeling problem without any results in my org.
The model first should be developed based on time (in M or W) in x axis and booking counts across y axis.
Next it has to be identified ...
2
votes
1
answer
50
views
Generate prediction intervals for a simple moving average model
I'm using a simple moving average to generate a forecast. Say I have $t$ observations. Then the forecast for time $t+1$ is given by
\begin{equation}
\hat{Y}_{t+1}= \frac{Y_t+Y_{t-1}+\dots Y_{t-m+1}}{m}...
- 21
3
votes
0
answers
50
views
Interpreting the output of scoring rules
Assume we have a probabilistic forecast for a continuous variable. Now we want to validate how good our estimate was. For that, we can use various scoring rules (e.g. CRPS, logarithmic score) or if we ...
- 31
0
votes
0
answers
15
views
RNN: How to feed multiple different time series to the network?
I'm new to RNN's and asking for advice on how to feed data to an RNN such as a LSTM.
I'm trying to forecast wind speeds at one location. For this location i have historical values as a time series. ...
- 23
0
votes
0
answers
29
views
Is time series regression closer to forecasting or classification?
I'm working on multivariate time series regression task.
The literature for it seems quite light compared to the problems of Time series classification (using algorithm like rocket for example) and ...
- 133
0
votes
0
answers
7
views
Forecasting model to categorize promotions - do I need one or two forecasting methods, one for prediction and one for inference?
I have a project where I'm trying to do two things:
Create a forecast for sales
Categorize the value for promotions
The data has a weekly seasonality, but it's a totally irregular seasonality. I ...
- 79
1
vote
0
answers
14
views
How can I condition an autoregressive vector model given past observations?
I'm trying to predict the scores of a soccer team in the next match using a VAR (Vector Autoregression Model). So my first attempt was to define the model as it follows:
$$g_{1,t}=\alpha_{1}+\beta_{11}...
- 11
0
votes
0
answers
7
views
Maximizing Number of Forecasts, but not too great a cost
I wanted to ask is there a name for the following problem:
Suppose, I have a prediction model, which makes a prediction, when certain preconditions are met.
Naturally, the goal is to maximize the ...
- 1
0
votes
0
answers
19
views
Multivariate forecast vs. forecast with exogeneous factors
If I wanted to forecast sales in a grocery store and I knew factors that would influence grocery sales, would there be a reason why I should use a multivariate time series model vs. time series models ...
- 167
1
vote
0
answers
18
views
How can I call a point in the future of a time series that I would like to forecast?
I'm a beginner in time series forecasting and I'm not sure if I understood correctly the meaning of forecast horizon. I was considering horizons as points in the future for which we would like to ...
- 566
0
votes
0
answers
14
views
error metrics resulted from time series forecasting as feature
While reading a paper about Time Series Anomaly Detection (https://www.usenix.org/conference/atc19/presentation/zhang-xu) I came to this :
"Forecasting error features: Following the prior work [...
0
votes
0
answers
24
views
Simple mean model for time series prediction
I have some historical dataset where I have the measure of a concentrate at different times of the day and I just want to create a simple model to predict the measure in the future.
So, the ...
- 4,450
1
vote
0
answers
55
views
1
vote
0
answers
13
views
Temporal cross-validation in forecasting: model selection, hyperparameter tuning and comparison to independent forecast
I'm mainly working with time-series models and want to make sure to build the correct model selection process.
Let's consider a forecasting problem and I have two model candiates, Model A and Model B. ...
- 11
0
votes
0
answers
22
views
time series forecasting: how to evaluate performance on test set
Performance during the training of a model for time series forecasting can be computed simply considering the difference at each time $t$ between the real value $y_t$ and the model predicted value $\...
- 655
1
vote
0
answers
24
views
Forecast Assistance given Monthly Time Series Data
I'm looking for some help to determine what type of model I should use for the given data set:
...
- 167
1
vote
0
answers
51
views
What does it mean forecast horizon in time series forecasting?
I'm a beginner in time series forecasting and I'm not sure if I understood correctly the meaning of forecast horizon.
I was considering horizons as points in the future for which we would like to ...
- 566
1
vote
0
answers
47
views
Scoring Probabilistic Forecasts - Can we infer a standard deviation from the 84.1 quantile prediction?
I am trying to compare forecasts of a series, and have several trained estimators which are deep neural networks with arbitrary architecture.
I'd like to compare the accuracy of their probabilistic ...
0
votes
0
answers
16
views
What does this statement about a forecasting lead time mean?
The ARPA-E PERFORM datasets produced by NREL contain both historical and forecast data on load, wind power, and solar power. NREL offers the following piece of information about the day-ahead forecast ...
- 648
2
votes
1
answer
34
views
What exactly is a "persistent/persistence model"?
I'm new to time series forecasting and only got previous experience with image processing in therms of neural networks. My goal is to do create an ML forecasting model for time series data. Currently ...
- 23
0
votes
1
answer
31
views
Learning a stochastic pattern in a count TS using DeepAR [duplicate]
I am trying to the learn the following pattern of count time series of vehicle demand every hour.
The count time series is generated from a negative binomial distribution with parameters n = 9 and p =...
- 211
3
votes
2
answers
289
views
R and Time Series Analysis; Suggestions for forecasting a series with a shock
I believe that the reprex below is self-explanatory.
I would like to extend a monthly time series by forecasting the next 3 data points.
The series is rather volatile and it spikes during the last ...
- 193
0
votes
0
answers
17
views
Unexplainable cyclical patterns on prediction intervals for time-series forecasting using Extreme Gradient Boosting regressor
I am following the documentation of skforecast to make time-series forecasting using the Extreme Gradient Boosting regressor (i.e., ...
- 1,097
1
vote
1
answer
23
views
For time series forecasting using machine learning, is feature engineering only needed for the y variable or is it needed for all x variables also?
Say I am trying to predict house prices (y variable) using population growth and GDP (x variables) using XGBoost or Neural Networks. All 3 are time series. I understand that I have to feature engineer ...
1
vote
1
answer
45
views
For time series, is non stationary an issue for machine learning models like they are for traditional time series models like ARIMA?
Sorry if the question seems basic. I understand that non stationary data is a big issue for traditional time series forecasting methods like ARIMA and VAR but is it the same for machine learning ...
0
votes
1
answer
31
views
How to determine the appropriate forecasting techniques for non-stationary univariate time series data?
I am new and I don't have background in time-series analysis or machine learning. Therefore, I am posting this question here:
I have three time-series data.
...
- 103
0
votes
0
answers
23
views
Having trouble finding the correct Auto ARIMA model to use
I have tried a lot of different models so far, but I'm having trouble finding the correct one. The problem is that RMSE is relatively high when I compare it to validation set.
Here is the data:
...
- 167
0
votes
0
answers
25
views
Forecasting retail product sales to inform how many of which product SKUs to manufacture
This is my first post here, and I'm coming in with a bit of a wicked 'problem'. Basically, I am writing a consultation-style report for a fashion brand based in London and I want to be able to ...
- 1
0
votes
0
answers
16
views
multivariate vs multiple time series - term explanation and forecasting model
Here is the time series I have: (p1s is an abbreviation of product 1 sales in dollars)
...
0
votes
1
answer
28
views
Learning stochastic pattern using RNN
I have a pattern of count time series of vehicle demand as shown below.The time series is generated as follows:
Categorical Random Variable, x = {0,1,2} and p(x) = {0.6,0.3,0.1}
low vehicles = 1 + x , ...
- 211
0
votes
0
answers
7
views
Regressing Singular Spectral Analysis Eigenvectors on data
I'm trying to model some time series economic data using mostly regression with other independent variables following the Error Correction Model (or Engle Granger approach). The ultimate goal is to ...
- 11