Questions tagged [forecasting]
Prediction of the future events. It is a special case of [prediction], in the context of [time-series].
2,968
questions
0
votes
1answer
16 views
α, β in ARIMA(0, 2, 2)
I saw 2 types of formulas for ARIMA(0, 2, 2):
$$Ŷ_t = 2Y_{t-1} - Y_{t-2} + (α + β - 2)e_{t-1} + (1 - α)e_{t-2}$$
and
$$y_t = -θ_1e_{t-1} - θ_2e_{t-2} + e_t \quad\quad (with \space y_t \space being ...
0
votes
0answers
6 views
How to calculate average growth and average growth rate. Use the results to predict the figure for the next two years in line?
I'm trying to do what I described in the title of this question.
I got the following table which I filled, but I'm not pretty sure how to "predict" what's going to happen in the next two years.
For ...
0
votes
0answers
11 views
spatiotemporal/geophysical forecasting
I am wondering what models to use for geophysical forecasting? I am looking at historical sea surface temperatures over the globe with one datapoint per month, so an input of (lat, lon, # of months) ...
2
votes
0answers
23 views
Extrapolation: why does being “outside” matter?
Extrapolation is often defined as predicting the value of an unknown function outside the range of available points. Let's say we are training on $x_1, .., x_n$, $x_{max} = \text{max}(x_i)$, $x_{min} =...
0
votes
0answers
16 views
Please help me Fitting an ARIMA Model with this data
I'm need of some help
I keep getting errors that require fitting ARIMA models using this data(Quarterly data of Korea's GDP from 1982). Someone tell me the source...I'm so confused...
data download ...
0
votes
0answers
9 views
Should stationarity be checked for *both* time series models (ARIMA, ECM…) and causal models with explanatory variables?
I read this paper that discusses if Time Series models or Causal models are the best for forecasting GDP.
I am familiar with unit root tests (ADF, PP) and stationarity test (KPSS) applied to a time ...
0
votes
0answers
10 views
+100
How to calculate gradient for custom objective function in xgboost for FFORMA
I'm trying to build an implementation of the Feature-based Forecast Model Averaging approach in Python (https://robjhyndman.com/papers/fforma.pdf). However, I'm sort of stuck on computing the gradient ...
1
vote
0answers
11 views
CNN Models for forecasting
I'm looking to know the new state of art in forecasting using CNN Network.I treid very hard but I couldn't find what I can consider as state of art.
thanks in advance
0
votes
1answer
12 views
Computing aggregated MASE for multiple time series
I think I understand how MASE works when I have a single time series. But what if I have several, for which I want to obtain an overall accuracy measure?
It's straightforward to compute an aggregate ...
0
votes
0answers
6 views
How to do time series modelling for different categories?
I have sales data for 200 consecutive days which I can assign to a specific state. My first attempt was to model some NN on and use the first 160 datapoints as train and the rest as my test set. ...
0
votes
0answers
26 views
Tiime series forecasing methods for small sample
I have real time data source that emits numeric values every 5 seconds. I wanted to raise alert whenever, for example the last 5 consecutive values, deviate more than a certain level. As you can see ...
1
vote
1answer
25 views
Does multivariate time series forecasting occur in parallel in a Neural Network?
It is common to give some multivariate time series to a Neural Network and get predictions for each individual time series. But my question is, does the NN take all series in consideration when ...
0
votes
1answer
18 views
Difference between h and T in harvey adjusted Diebold and Mariano test?
I am looking into comparing the predictive accuracy of forecasts of different models against a benchmark model. For this I have looked into the Diebold-Mariano test statistic, however I am using the ...
0
votes
1answer
59 views
Fixing convergence in SIR model using modified fit-model to fit COVID-19 data
I'm trying to model the data for covid-19 using SIR model in R. I followed the answer of the question, and the blog. I'm using the suggested code, However, the data does not converging. Any suggestion ...
0
votes
0answers
20 views
Predict peaks within a time series
I'm looking for a different approach to linear regression, but I don't know how to model and implement my data. I would like to predict spikes in CPU consumption in a time series using LSTM or newelm. ...
0
votes
0answers
17 views
What does my ACF and PACF plots indicate for ARIMA order?
I am looking at forecasting first-order differences oil prices using the ARIMA models. However, I struggle to see what p and q orders my ACF and PACF plots would indicate.
I have added the act and ...
0
votes
1answer
13 views
Does the method of reruning GARCH models every day (to update parameter values and improve out-of-sample forecasting performance) have a name?
It is my understanding that normally GARCH models make forecasts for say T-K days ahead. Instead of doing that I would like to use the data for days 1, 2, ...,k in my dataset to fit a GARCH model to ...
0
votes
0answers
11 views
How to do probabilistic forecasting in R? [closed]
I am a beginner to probabilistic forecasting. From my research I have a vague idea that monte carlo simulation can be done for injecting uncertainity in the process. Do i need to get multiple point ...
0
votes
0answers
13 views
Time series forecasting LSTM small dataset
I'm new to machine learning, i'm trying to use LSTM to forecast the power production of a solar power plant, i have a small dateset that contains 7200 rows and 4 columns, i divided the data into ...
2
votes
0answers
23 views
Where did I go wrong when using ARMAacf function in R? [closed]
I recently had an exam in forecasting where I was one point short of an A. The biggest mistake I made which cost me 3 points was that I incorrectly used the ARMAacf() function to calculate the implied ...
1
vote
0answers
14 views
Forecasting for future periods with machine learning models - how to treat input variables
I have a dataset of X1,X2,X3,etc. to predict the number of units, and one or some of my X variables are lagged versions of the units (my Y variable) I am trying to predict in addition to other ...
0
votes
0answers
18 views
SARIMAX giving predictions which doesn't match the data inputs
I am building a SARIMAX model on the data which is monthly aggregated. To select the best params, applied a grid search to select the best parameters. Once I get the best parameters for the data I am ...
1
vote
0answers
13 views
Convert inputs ANN to time series for forecasting [closed]
I want to ask about artificial neural networks, ANN. Do I need to convert inputs of ANN to time series if I want to do forecast ? Thank you in advance for answering my question.
0
votes
1answer
32 views
How to simulate forecast error when then the distribution of error is not normal?
I am using a regression model that produces non-normal forecast errors. To produce different scenarios, I need to simulate the model error, I can bootstrap from historical errors, however, because the ...
1
vote
1answer
22 views
Forecasting sales of new products - how good do my experts forecast my sales?
I want to forecast the sales of new products. Last year I used an expert rating to predict the sales of 10 new products. The ratings were used to dicide how many percent of the total sales should be ...
0
votes
0answers
17 views
age-sex-region multivariate time series modelling
I am trying to model heart disease mortality rate time series based on features like obesity time series, hypertension time series, and so on.
The data is age-sex-province specific which means for ...
0
votes
0answers
8 views
Train one model across number of the datasets with multiple features time series of diffrent duration, using categorical metadata
I'm trying to create model for prediction multiple correlated time series features.
Issue is that input dataset consists of a number of "projects" with different duration and different categorical ...
0
votes
0answers
19 views
Time series forecasting how to structure train test sets for a year of predict
I have three years worth of data (2017-2019) and the goal is to create a model that can predict out the next year. I am having trouble understanding how to structure my train test splits given this ...
1
vote
0answers
19 views
Forecasting with Irregularly Missing Data
Suppose I am supplying $N = 1000$ vendors, and I am looking for a way to predict their demand for my product over $T = 90$ days. Concretely, I hope to take some features for each vendor, such as their ...
1
vote
0answers
15 views
How to build a function with the result of arima in R?
I use: arima(y, order = c(3,1,1) in R to get ARIMA(3,1,1), result as follows:
Call:
arima(x = y, order = c(3,1,1))
Coefficients:
...
0
votes
0answers
4 views
When is High Sensitivity Rate preferred over High Hit Rate? [duplicate]
I've been told by my professor that in real-life deployment, hit rate is very important but sensitivity and other accuracy rates need to be satisfactory also. However, my other professor also says ...
1
vote
0answers
23 views
Help with VAR Forecasting
community! I am using VAR, I want to forecast how my variable "Arbeidsledighet", which means Unemployement is playing out while having a "shock" in my other variable, "Oljepris" which basically means ...
0
votes
1answer
31 views
auto.arima error: 'Error in solve.default(res$hessian * n.used, A) : Lapack routine dgesv: system is exactly singular: U[1,1] = 0'
I am trying to fit a dynamic forecasting model using auto.arima but I am getting the following error when trying to run my code:
'Error in solve.default(res$hessian * n.used, A) : Lapack routine ...
0
votes
1answer
42 views
Forecasting sales
I got 95 weeks of sales data (i.e., 95 data points) for a retail business, whose plot looks like this:
Sales are evidently seasonal. Also see plot for Year 1 against Year 2 Sales by Week of Year
I ...
0
votes
0answers
13 views
Solving the Forecast for Next Period Using the ARIMA Model
Mr. Tan built an ARIMA model to fit the price of fund XYZ. The parameter estimates he obtained are shown in Table 2-1. Write down the ARIMA model, and predict the fund price for the next period if the ...
0
votes
0answers
2 views
Backcasting or Not?
I'm doing a research about the relationship of Female Wage Gap and Internet from 1995-2018 (yearly) with fixed effect model. I found some missing data from 2 variables in 1995-2000. Should I do ...
0
votes
1answer
50 views
Differences between Dynamic Regression Model and Intervention Model?
I am currently studying on dynamic regression and intervention model but I haven't have much resources on hand about the differentiating both of them. I understand that intervention model is a special ...
0
votes
1answer
23 views
Identifying ARIMA model from ACF and PACF
I've identified this as a AR(1) model as the ACF clearly shows a slow decay and the PACF seems like a cut off after lag 2. However, can it also be a ARMA (1,1) model because PACF seems like a damped ...
1
vote
0answers
30 views
Forecasting Validation
question on validating forecast models. The traditional approach (https://otexts.com/fpp2/forecasting-on-training-and-test-sets.html) is to hold-out n number of samples from the end of your time ...
0
votes
1answer
23 views
Identify the specific ARIMA model for the following ACF and PACF plot?
Hi. I've identified this as a AR(1) model as the ACF clearly shows a slow decay and the PACF seems like a cut off after lag 2. However, can it also be a ARMA (1,1) model because PACF seems like a ...
0
votes
0answers
9 views
minimax estimator in applications
In the applications, does it really matter if the estimator is minimax or not if, say, we are interested in forecasting and with current non-minimax estimator we have better out-of-sample scores?
0
votes
0answers
12 views
Multi-Step-Ahead Forcasting of Differences (RNN)
I am trying to implement a hourly-forecasting model for a hydrological prediction.
Therefor my data has following features: rain-precipitation & temperature from 10 measurement stations within the ...
1
vote
0answers
14 views
Should I re-standardize data when updating LSTM model with new data?
I'm fitting an LSTM for timeseries data and I'm hoping to train it "dynamically"—e.g. train it initially and then re-train/update with the next timestep when I get that data. Right now I'm fitting the ...
0
votes
1answer
13 views
Prediction interval for Combined forecast of univariate time series
I have made a combined forecast of a univariate time series. I used ETS, ARIMA and STL and take a simple average of these means and get a combined point forecast 12 months ahead.
My question is. How ...
0
votes
0answers
70 views
Aggregate time-series forecast from individual probabilities
I'm conceptualizing a methodology for a time series forecast but I lack the terminology and even the notation to learn more or even adequately describe it.
Suppose I aim to forecast the aggregate ...
1
vote
1answer
34 views
Why SARIMA has better accuracy on weekly dataset than on daily one?
I am studying time series right now. So, I have this dataset. My aim is temperature prediction.
I've found out that ARIMA can't work with long period seasonality. So, I've resampled daily dataset ...
0
votes
1answer
22 views
How to forecast intermittent demand when the future days with 0 demand are known in advance
I have an intermittent time series of the demand of some products. I have read some very useful answers (such as Forecasting Intermittent Demand with zeroes in times series ) as to how one would go ...
1
vote
0answers
21 views
Density forecast AR(2) model estimated through MCMC Gibbs sampling
Say that I have my one-step ahead forecasts from the iterations of a MCMC Gibbs Sampling algorithm for my AR(2) model. Until know I have taken some percentiles (median, 25th percentile, 75th ...
2
votes
0answers
83 views
Regression: Causation vs Prediction vs Description
In my experience it seems me that the interpretation about regression, its meaning and its scope, are debatable and great confusion exist about those things. It seems me that confusions are not go ...
0
votes
1answer
17 views
Can we use the results achieved in forecasting after employing min-max normalization on data?
I am working on time series forecasting with univariate data. After applying min-max normalization, I am getting results in terms of Mean Error, Root Mean Square Error etc, less than 1 of course and ...
