Questions tagged [forecasting]
Prediction of the future events. It is a special case of [prediction], in the context of [time-series].
3,579
questions
0
votes
0
answers
6
views
Are stacked meta models for time series forecasting still considered forecasters?
I am working on building a meta model that is based on the principle of stacked generalisation (1). In a nutshell, this method works by using building a meta model based on the predictions of various ...
- 63
0
votes
0
answers
13
views
Outlier Treatment and Forecasting
I have come across multiple methods regarding outlier treatment:
(features = my input/regressor/... matrix)
Treat outliers in the entire sample (both features and the variable to be forecasted).
...
- 860
0
votes
0
answers
9
views
identificar y estimar, validad, predecir y comparar con Alisado. ARIMA
I would like to know if there is a function that can filter work days in my temporary serie. I need to include 2 intervention variables, easter days and work days, in order to estimate with Arima I ...
- 1
1
vote
0
answers
26
views
Mean-level forecast from rugarch does not match manual calculation
I am looking into the rugarch package and am trying to understand how the one-step-ahead forecast is calculated.
Specifically, I am fitting an AR(2)-GARCH(1,1) ...
- 11
2
votes
0
answers
19
views
When do ARMA models fail?
I have just started learning about Autoregressive–moving-average model (ARMA). On the Wiki page, it has been mentioned that:
ARMA is appropriate when a system is a function of a series of
unobserved ...
- 211
1
vote
1
answer
16
views
Is ARIMA-GARCH nested within ARIMA?
I wanted to compare ARIMA(1,1,1)-GARCH(1,1) and ARIMA(1,1,1) model forecasts with a Diebold-Mariano test, but I know that it cannot be used for nested models. Is ARIMA-GARCH technically nested within ...
- 25
0
votes
0
answers
15
views
Statistical test for forecast performance over multiple runs
Lets say I have a time series, create a training and test set, and I want to compare the predictive accuracy of two models, by measuring e.g. the mean absolute error (MAE) over the test set. I know ...
0
votes
0
answers
19
views
How to forecast sales for entire current month taking into account sales from half of month?
Good afternoon!
I want to forecast sales for current month. Since I already know sales for two weeks of current month, I want to incorporate this information into forecast for the whole current month, ...
- 93
0
votes
0
answers
13
views
Over forecasting when using historical data during the pandemic period?
I am new to the forecasting domain. I am dealing with a forecasting task where we had a very high abnormal demand for our products during the pandemic. However, in recent months, the demand trend is ...
- 101
1
vote
0
answers
22
views
Why does my ARIMA predictions on monthly data form a straight line?
For short detail, the goal was to forecast using 51 monthly observations of KPI of project implementations which I aggregated by sum from 463 observations from about 4 years of data (May 2017 to July ...
- 11
0
votes
0
answers
17
views
Time series forecasting for revenue forecasting?
I am currently working on a project where I have to forecast the revenue for (the duration of) projects within the organisation. The organisation has several departments that occupy themselves with a ...
- 1
1
vote
1
answer
26
views
How to predict multiple future values in a linear model in R?
So i currently have a data set consisting of the Year, Credit Hours, and Number of students. I have been trying to predict future credit hours by the number of students.
...
- 11
0
votes
0
answers
7
views
How to aggregate a categorical variable as external regressor for a hierarchical/ grouped time series?
I have been working with a hierarchical time series, relating to a set of identical products in a number of stores. For this purpose when we aggregate the data set based on 2 attributes like "...
- 223
1
vote
1
answer
27
views
Shall I use daily or monthly data for demand forecasting?
Let's say we want to forecast sku-level demand one year and four months ahead, and we have daily demand data for the last 3 years.
Taking into account that most daily time series at sku-level contain ...
- 11
0
votes
0
answers
19
views
Why drop the year 1898 from this dataset? [closed]
[
This is an exercise. They suggested to drop the value of the 1898. But it looks like a normal year, except for the sudden drop in the levels in the following years. So then if we drop 1898, based ...
- 11
0
votes
0
answers
16
views
What would be best the best way for multiple companies to consolidate their demand forecasting together?
I am currently reading up on my demand forecasting knowledge and had this question where I can't seem to find a quick answer for.
Let's say you have a couple of stores/restaurants/etc that sell more ...
- 1
0
votes
0
answers
15
views
Forecasting with ugarchforecast
I'm a bit confused on how to use the ugarchforecast function for forecasting. I estimated a GARCH(1,1) model based on the training dataset (...
- 25
0
votes
0
answers
13
views
In SARIMA model do we start by first differences or seasonal differences?
I don't know the general formula for SARIMA model for additive and multiplicative model.
I don't know whether we start by first differences or seasonal differences.
I only know the formula of ...
1
vote
1
answer
41
views
Forecasting based on few samples
I have to forecast number of enrollments for an international univeristy , challenge is there are only few years of data.So, my data looks somewhat like this:
...
- 29
0
votes
0
answers
21
views
0
votes
0
answers
16
views
Time Series forecasting with multiple non-parallel input
I have a private dataset describing more or less 200 different crowdfunding projects.
In such data, I have the trend of donations (so are uni variate) over time for each project.
The problem is that ...
- 1
1
vote
0
answers
18
views
R: Fable - forecasting hierarchical time series with transformation
I have a hierarchical time series, with two sub-series that have significantly different behaviours. One subseries would definitely benefit from Box-Cox transformation to stabilise the variance.
Is ...
0
votes
0
answers
17
views
Under what conditions will prices of shares in a binary prediction market accurately represent probabilities?
I often see that prediction market sites say that the prices of the shares on outcomes can be interpreted as the likelihood of the outcome occurring.
But under what conditions is this true?
- 1,048
2
votes
0
answers
14
views
Statistical test for temporal cross validation
I estimated the performance of my forecasting model and that of a baseline on 10 folds using temporal cross-validation. With which test do I assess if my model is significantly better than the ...
- 423
0
votes
0
answers
14
views
Understanding Auto-Regression in details
I was analysing the equation of auto-regression model, e.g. AR(1), so that:
Yhat = Beta0 + Beta1Yt-1
Lets say I have a 36 observation series and I want to forecast 3 periods ahead and Beta1 is 1.1 (...
- 31
1
vote
1
answer
38
views
time series forecasting model cannot beat baseline
I am doing some time series forecasting task up to 4-week ahead (in weekly scale).
However, I think that even if I fit a ARIMA model (with some optimisation on selecting parameters) to the time series,...
- 111
0
votes
1
answer
20
views
1 Stationary time series, 1 non stationary: do I need to transform BOTH, OR can I use VAR with 1 transformed and 1 stationary variable?
I am doing a time series forecast using VAR. I have 2 time series, "orders" and "calls"
The orders time series is stationary
The calls time series is non-stationary
Let's say I use ...
1
vote
0
answers
16
views
How to compare different models in their ability to forecast the value-at-risk with Diebold-Mariano test?
I made value-at-risk forecasts for different models for the 95, 97.5 and 99%. I also made a dummy which equals 1 if the true return was below the value-at-risk, 0 otherwise.
How can I compare those ...
- 41
1
vote
0
answers
25
views
Causal impact: noisy controls lead to strange results
I am using R causal impact to measure the effect of a campaign intervention. Doing some tests, I found some consistent but very strange results.
What I did is to generate a time series with weekly ...
0
votes
0
answers
12
views
Updating temporal embeddings depending on the input
I'm building a forecasting model and I'm using a temporal embedding along with a positional embedding following the same architecture as Informer. ( https://arxiv.org/abs/2012.07436 )
My problem is ...
0
votes
0
answers
26
views
Communicating probabilistic information through a forecasting service
Imagine that we were to build a forecasting service for a public transportation company. For a given set of passenger terminals $V$ scattered across a region, the forecasting service predicts the the ...
- 191
0
votes
0
answers
40
views
Arima model not showing seasonality in its forecast
The following is a seasonal(not perfectly) time series sequence that I am trying to fit an ARIMA model to:
I performed box-cox transformation, 1 seasonal differencing and 1 regular differencing to ...
- 13
0
votes
1
answer
38
views
Why does the performance of `prediction_in_sample()` very different from `predict()` in ARIMA models
I try to use prediction_in_sample() in an ARIMA model (python package pmdarima) to estimate the whole time series and ...
0
votes
0
answers
17
views
During a poll, what is the percentage of examinated ballots needed to be 99% sure about the winner?
It's a simple question but hard to explain. At the end of a (say, political) poll n candidates will receive their respective percentage of votes, according to ballots. At this point, all the ballots ...
- 111
0
votes
0
answers
11
views
Predictions after identifying an appropriate time series model
I have a very simple question that I can't find the answer to - I hope you can help. Let's say for example I have a timeseries that I would like to make some future predictions on. I split the data 80-...
0
votes
0
answers
11
views
Iterated direct forcasting with R
I am trying to forecast the next ten periods of a time series past the end of my data using an AR(4) model.
My code so far follows as:
...
- 1
0
votes
0
answers
10
views
Is ARIMA the right model to use for the questions I am trying to answer?
I am looking for guidance or suggestions on the best model or method to solve the questions below.
My dataset is a time series that contains date, number of orders, and number of Customer Service (CS) ...
0
votes
0
answers
14
views
Discrete wavelet transform - DWT (beginner)
I recently stumbled upon this article :
[https://www.bportugal.pt/sites/default/files/anexos/papers/wp201612_0.pdf][1]
In the paper they use DWT and I am having trouble understanding how to construct ...
0
votes
0
answers
18
views
One step ahead forecasting - VAR
Hi I am exploring VAR functions from vars packages
Ive a model fit using following command
model_fit <- VAR(diff_raw_prices, p = 5, type = "none")
Now ...
1
vote
1
answer
36
views
Inverse differencing and inverse box cox on forecasted arima predictions
I am working on a time series project with non-seasonal data which has a non-constant variance. So in order to solve that issue I used box cox transformation to get the data in a suitable format,
<...
- 13
0
votes
0
answers
8
views
Best model(s) & suggestion for correlation between two variables , "lag" effect, & forecasting time series
I am looking for guidance or suggestions on the best model or method to solve the questions below.
My dataset is a time series that contains date, number of orders, and number of Customer Service (CS) ...
0
votes
0
answers
7
views
Determining climate change effect on mortality rate time series
I am currently conducting research in determining the impact of climate change on mortality. I have got time series of the number of deaths for different age groups which dividing them by their ...
0
votes
0
answers
25
views
Why does my data look the same after log, root, Box-Cox transformations?
I have to forecast the amount of cars sales for the next 12 months. The data I have gathered are from 2013-2021 (108 months). This is what the plot of my data looks like using Rstudio and its ...
- 21
0
votes
1
answer
45
views
Forecasting using Copula GARCH methods
I need to replicate what Huang and al (2009)* did without using built-in functions in R. What I'm struggling with is how to forecast returns for my two data samples. I've found the GARCH specs and ...
- 1
0
votes
0
answers
15
views
What's a Heterogenous time series and how does Lagrange multiplier test statistic relate to it?
I have two time series with me. Running analysis with fb KATS time series Analysis module, I get below values for heterogeneity.
...
- 183
0
votes
0
answers
25
views
How to forecast actual future values using XGBoost?
So I have a solar Irradiation dataset having around 61000+ rows & 2 columns. I have made the model using XGBoost to predict future values.
I have split the data in 2 parts train and test and ...
- 1
0
votes
0
answers
14
views
How can I do a comparative analysis of fbprophet time-series model results in pyspark? [closed]
I am using fbprophet for time-series forecasting on an unique ID of a big data with thousands of unique ...
- 101
0
votes
1
answer
39
views
What is the best way to forecast birthrates for the next 10 years?
I am new to forecast modeling and was curious what sort of model/modeling procedure would make the most sense for forecasting birth rates into 10 years into the future.
It seems to me like birth rates ...
- 1
1
vote
1
answer
28
views
Multiple correlated multivariate time series
I have forecast dataset containing multiple multivariate time series that are not independent from each other. A state in one of the the series in time "t" can influence the state in another ...
0
votes
1
answer
29
views
Differencing my training set data
I'm trying to difference the non-stationary data in my training set with ndiff() and nsdiff(), but R returns the following:
Warning: The chosen seasonal unit root test encountered an error when
...
