Questions tagged [forecasting]

Prediction of the future events. It is a special case of [prediction], in the context of [time-series].

Filter by
Sorted by
Tagged with
2
votes
0answers
19 views

Forecasting with empirical copulas

I estimated the beta copula with 3 variable time series. Now I'd like to make forecasts to evaluate the out-of-sample performance of my model. I know 2 of the 3 variables and I have the dependence ...
2
votes
0answers
23 views

Pre-Whitening results not conducive to white noise property [closed]

I have these two time series(df_errror,df_booking) (both are non-stationary, seasonal) that I want to prewhiten and then find cross correlation: I used this code for auto_arima for df_booking: ...
0
votes
0answers
25 views

Error terms and Residual in Time Series

I started learning Time Series Forecasting and the below questions keep my head confused a lot. Many papers mention that the forecast errors have to be normally distributed and what about the white ...
1
vote
2answers
121 views

Is there any standard / criteria of good forecast measured by SMAPE and MASE?

I have built a forecasting model for a company. Since it is dedicated to practical usage, I prefer to use the relative error parameter (like MAPE, SMAPE, & MASE) as a measurement for my model ...
4
votes
1answer
61 views

Predictions and forecasting with mixed-effects models

I am not sure I fully understand how mixed-effects models (such as mixed-effects PK/PD models) can be used for forecasting. Some notations Let $p \in \mathbb{N}$ with $p \geq 2$. We assume that for ...
-2
votes
1answer
66 views

No ARIMA model fits my data

I tried to fit an ARIMA model to a data, but no success!! I shared my data and the R-codes below to check any mistake! dt=c(15,18,13,16,11,14,19,20,16,17,13,11,13,15,8,12,15,14,15,15,18,11,13,15,11,11,...
0
votes
0answers
8 views

ARIMA(0,0,0) model with multivariate covariates?

Lets start with my dataset in which the first column, Y, is a time series observation along with 10 covariates, X1, X2, ..., X10. In fact, I have multivariate regressors and wanted to fit a times ...
0
votes
2answers
33 views

Plot of prediction by ARIMA model [closed]

After fitting an ARIMA model to data, how can we plot the predicted value plus the original observation in one figure? ...
0
votes
0answers
17 views

Is there a way to find the most adapted NN?

I'm trying to build a NN that uses one or two time series to predict the value of another one, using history. For example, in the next graph : Blue is the input Orange is the predicted output Green ...
1
vote
1answer
50 views

ARIMA model with multiple covariates, XREG

I have shared the main data d2015.txt, includes 5 columns. The first column is the $y_t$ the time series observation. The 2nd to the 4th column is the covariates/regressors and the fifth column is ...
0
votes
4answers
53 views

Accounting for uncertainty in evaluating a forecast

I'm new to forecasting and I have some (probably very) basic and generic questions. I'd appreciate some references that get into details of this too. Using some model to forecast a time series, I ...
0
votes
1answer
22 views

Which data to use for forecast - Test/Train data

I am fairly new to R and I am trying to develop forecast models after the model is selected based on accuracy, do we use the entire historicals for forecasting with the selected model? Or do we use ...
0
votes
0answers
13 views

To what extend can pre-training and training affect the results of a prediction model?

If we pre-train a model forecasting COVID-19 with data of SARS, which had a different transmission pattern, will our model be weakened? If we train the same model with data of (for instance) the USA, ...
0
votes
0answers
22 views

Is it possible to create a general forecast model working on several data sets?

I am working on a project, where the task is to create forecast models that can be used on a wide variaty of data sets. Some of which are stationary and some which aren't. Both ARIMA and Exponential ...
0
votes
2answers
38 views

R forecasting: List of supported or available models from fable package

Is there a complete list of all available models within fable package? ...
1
vote
1answer
33 views

forecasting with optimised theta method (otm) using time series cross validation with R

I want to do an out-of-sample forecast experiment using the optimised theta method (otm) on a time series. Further, time series cross validation with a fixed rolling window size should be applied. ...
2
votes
2answers
83 views

Inference in Time Series: Prophet vs. ARIMA

I read through Prophet's white paper and they mention that their algorithm, "gives up some important inferential advantages of a generative model such as an ARIMA." (page 7) So now I'm ...
1
vote
1answer
38 views

GARCH forecast of series (in R) seems too high

I am wondering why the mean of my model is so high leading to a high forecast of the time series data. I included a linear regression in the external regressors as there is a clear downward trend. I ...
0
votes
1answer
28 views

Project time series from previous time series examples and characteristics

Say I want to open a shop but first I want to project the likely sales in the first 5 years to see if it is a viable option. I have data pertaining to 100s of other start ups, including their success ...
0
votes
0answers
21 views

ARIMA interpreting results and how to out-of-sample forecast

I am trying to learn ARIMA using Python and the data in https://www.kaggle.com/c/demand-forecasting-kernels-only. I'm using the sales for Store == 1. Here is how the data looks like: Here is my ARIMA ...
0
votes
0answers
15 views

Interpreting Autocorrelation W/ Detrended Seasonality Regression Model in R

I've built a seasonality regression model with the goal of creating a seasonal index table. My model methodology first detrends the data then regresses the detrend values on 11 monthly seasonal dummy ...
0
votes
2answers
62 views

How do you determine that your timeseries forecasting model is good enough?

Pardon me, I am new to timeseries forecasting. Given that there is not always a clear cut way to know whether your forecasting model is good enough and there's a significant degree of subjectivity in ...
0
votes
0answers
35 views

auto.arima with regressors

A simple question, but I have not found it anywhere. I have worked with time series for a while, but am new to R. I want to predict future values of Y (all I care about are the forecast) when I ...
2
votes
2answers
201 views

Autocorrelation in residuals of a regression model with ARIMA errors (example in Rob Hyndman's book) - Part 2

Part 1 is here What does the forecaster do when there's correlation in the residuals of an ARIMA model that's used to model the errors from a regression model? Does this mean the forecasting approach -...
0
votes
0answers
16 views

Forecasting sales for thousands of stores individually with multiple features associated

I have data of 2000 stores with associated 145 features(example: ambience, holidays, no. of brands) and their monthly sales for 2 years. It means that for every store I have sales data and other ...
1
vote
1answer
27 views

Forecasting Sparse Demand Data: Cumulative sum transformation

I have many SKUs/products that have missing historical values. By missing, it means it has no data or order at all. I'm tempted to say intermittent but there are not regularly intermittent to make ...
1
vote
0answers
69 views

Any feedback on Google's “Temporal Fusion Transformers for Multi-horizon Time Series Forecasting” Model? [closed]

I am trying to build a time series model to help forecast the demand of semiconductor chip-level products of a semiconductor company. They have roughly 50 products and several variations of each ...
2
votes
2answers
34 views

How to test superior predictive ability over multiple time series?

Suppose you have two models, model A and model B, and let these models forecast 10 time series over a horizon of 12 periods. That is, suppose the time series contain monthly data and your forecasting ...
3
votes
2answers
134 views

Are there good methods to increase the weight of prior distribution in parameter estimation using Bayesian method

say, I have a prior distribution of parameter $\pi(\theta)$ Then, given observation $x_1,x_2,...x_n=x$, we have $\pi(\theta \mid x) \propto f(x \mid \theta) \pi(\theta)$, which is then used for ...
2
votes
2answers
107 views

Autocorrelation in residuals of a regression model with ARIMA errors (example in Rob Hyndman's book) - Part 1

I am a novice to time series forecasting and I need some help understanding something in Rob Hyndman's excellent Forecasting: Principles and Practice book (3rd edition). After fitting a regression ...
1
vote
1answer
24 views

How is modeling the time series error/variance, e.g. ARCH or GARCH models, different from modeling time varying forecast intervals?

I'm having a hard time understanding the intuitive difference between modeling the volatility or variance of a time series as it is done in ARCH and GARCH models: $$Y_t = c+\epsilon_t+\phi_1Y_{t-1}+....
1
vote
0answers
19 views

Research area about - Forecasting time series with added items

I'm wondering is there any time series research area about the change of forecasting with added items. For example, in the prototype below, when we check each recommended item, the forecast about ...
0
votes
0answers
38 views

What are some good models for stock price predictions?

For the fitting and forecasting of time-series data on stock price, the most frequent model I have heard of is ARIMA. ARIMA is actually conducting a regression of stock prices and residuals of stock ...
2
votes
1answer
32 views

Is summing daily forecasts a sound method for generating weekly/monthly forecasts?

I'm new to time series analysis, and I am wondering if this is a sound method for generating weekly and monthly predictions. In my case, I need to generate daily, weekly, and monthly predictions. If ...
5
votes
2answers
101 views

What are good resources for online time series forecasting? [closed]

I have a project in which I'm given the state of the order book for a stock every 1ms, and I need to predict the return on the stock 2 minutes in the future using this information. I haven't been able ...
0
votes
0answers
16 views

Forecast error variance for AR, MA, ARMA and ARIMA

Please could someone point me in the right direction of some resources that show how to derive the Forecast Error Variances for different types of models? I'm trying to create a list showing how to ...
0
votes
1answer
86 views

ARIMA forecasts with autocorrelated residuals

I have a time series on consumer price index (CPI) and want to forecast inflation which is in my case the first difference of the log of CPI: ...
0
votes
0answers
21 views

Long term time-series prediction for non-stationary but regular water flow data

I am looking at a very interesting time series dataset for the volume of water flow through some groundwater sensors. Our goal is longer term prediction of water levels, such as 1 - 5 years in the ...
2
votes
0answers
41 views

ARMA: order selection with LASSO

I'm trying to forecast daily data (I have 15 years of historical data) with complex seasonality: weekly, monthly, annual and also irregular seasonality due to moving events like Easter. As suggested ...
0
votes
0answers
11 views

How to calculate “Rolling Quartile” in a forecast

I have an hourly forecast (let's say it's for rainfall) projected for 40 years. I am using this forecast to plan an activity (for example: outdoor construction; you don't want to plan to be working ...
1
vote
0answers
34 views

Choosing between Multiplicative and additive Holt Winters model

I´m doing a prevision of the demand of a tool, I´m gonna use the Holt-Winters method but I am not sure about using the multiplicative one or the additive. I decided to isolate the seasonality by ...
0
votes
1answer
33 views

How can you know that result of auto.arima is accurate?

I’m using auto.arima and forecast package to forecast the COVID-19 dataset. I got my results and graphed them in R. As I’m no statistician, I read many papers available online related to COVID-19 and ...
0
votes
0answers
21 views

Can ARIMA be used to forecast future data points that are slightly more than the original observed data

my knowledge in statistics is limited and I'm trying to use auto.arima() in R to forecast COVID-19 data. My data set is 97 days and I'm trying to predict a total of 105 days that are divided into ...
1
vote
0answers
29 views

ARIMA Model Suitability Testing

I'm attempting to forecast 24-month hydroelectric generation at various river systems in the United States. Because river flows -- which is the primary driver behind hydro generation -- are mean-...
1
vote
1answer
49 views

Variable selection without strong theory: Can we do better than LASSO for prediction?

When a variable of interest has many plausible explanatory variables, and one lakes strong theoretical or subject-matter grounds for selecting among them, it is tempting to build a “kitchen sink” ...
0
votes
1answer
28 views

Understanding plot for stats::predict

I created a time series for 15 years (in each year 123 days), and I created a forecast using stats::predict for the next 5 years. ...
2
votes
1answer
31 views

Time series - Differencing vs Dividing

What is the difference between using differencing or dividing to treat trends / seasonality ? Most approaches seem to be using differencing. Is there a qualitative preference for why we do this ? For ...
0
votes
0answers
23 views

Forecasting with decomposition

I've been reading the book Forecasting: principles and practice. In chapter 6.8 the authors talk about forecasting with decomposition. I'm a bit sceptic about this. The reason I'm sceptic is that ...
1
vote
0answers
17 views

Forecasting monthly stock returns with daily data and down-sampling concerns

I have daily stock return data (log returns). I want to forecast returns for the next two months. I am creating forecasts with both univariate ARIMA and GARCH models with regressors. What are the ...
0
votes
0answers
15 views

Time Series Forecast for a time series getting updated

I am working on a forecasting problem, where i am planning to forecast the value for the current time step (real value 43 in data below in a[4] column). The data is in the form of values at each ...

1
2
3 4 5
61