Questions tagged [forecasting]

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

986 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
2
votes
0answers
4k views

auto.arima and Arima (forecast package)

I am facing a strange issue with the auto.arima() function. On a dataset named data, I run the following code ...
2
votes
0answers
267 views

Why only full ARIMA models in auto.arima?

It seems that the auto.arima function in the "forecast" package in R only considers full ARIMA models. By "full" I mean that if an AR lag $k$ is included, AR lag $j$...
2
votes
0answers
887 views

Panel data forecasting from Arellano-Bond GMM estimation

I want to come up with predictions of final energy demand per capita (fe) for a panel of countries. Explanatory variables are GDP per capita (gdp) and population density (pop) -- all variables are ...
2
votes
0answers
149 views

Ensemble model performs better with worse performing consitutent models?

I have a forecast model I am developing that uses some very unreliable input data, missing data (due to sensors or comms failures) is the rule, not an exception. The quantity being forecast is a daily ...
2
votes
0answers
973 views

Forecasting call volumes over short intervals using R

I am trying to do a basic forecast of call volumes using the forecast library for R. I am not having too much trouble forecasting on a daily or monthly interval, however when I try to forecast on an ...
2
votes
0answers
2k views

Forecasting daily data with trend, yearly, day of the week, and moving holiday effects

I'm expanding a question I posed earlier because I think it was lacking detail. I'm attempting to forecast daily demand for a restaurant that sells take away food, primarily to office workers on ...
2
votes
0answers
791 views

Overlap in time series training sets

I have a time series prediction problem where the aim is to forecast the average value of $y_t$ over the next $T$ periods, given all the information available up to point $t$. For example, I want to ...
2
votes
0answers
199 views

My prediction errors are correlated. Now what?

This is partly an R question and partly a stats question: I am trying to do batch forecasts using the auto.arima function from the forecast package. I have over 1000 items to forecast so doing it by ...
2
votes
0answers
904 views

Updating ARIMA model

My question is about updating the parameters of a regression with ARIMA errors model as new (monthly) data becomes available each month. Similar question were asked here before: Updating ARIMA ...
2
votes
0answers
72 views

Predict binary occupancy vector from history of vectors

I have a set of binary vectors where each vector represents one day of occupancy in a house and consists of 48 elements (each element for 30 minutes of the day). Each element can be 1 meaning that ...
2
votes
0answers
74 views

Forecast pricing data with lead times?

I have some "big data" containing event pricing information with 45 days of lead time quotes up to the day before the event. Thus, it's structured like so: -45 100.00 -44 120.00 ... -1 110.00 We ...
2
votes
0answers
567 views

Comparing non-nested models with out of sample likelihood

I recently read a paper in which the authors claim that in order to compare the forecasting performance of two non-nested models, models A and B, a valid procedure is to fit models A and B on the same ...
2
votes
0answers
66 views

Forecasting & social influence data/experiment - Seeking research strategies

In my experiment, individuals assign probabilities to the likelihood of future events, and update their forecasts as frequently as they like. Most questions stay open (receiving new forecasts) for ...
2
votes
0answers
100 views

Model from $\hat{Y}$s or model from residuals?

This is for modeling revenue by looking at historical data. I am trying to estimate a curve where $x$ = Fiscal Year Quarter and $Y$ = % of Revenue for lifetime of a bid(sale/opportunity/whatever ...
2
votes
0answers
275 views

Support vector machines and Granger causality

I was wondering if Granger causality would be an efficient tool for searching for relevant input data for an SVM system. For example if I want to forecast SP 500 returns, I could put in my input data ...
2
votes
0answers
733 views

Time Series Decomposition : Box Cox for Additive Decomp

Coming from basically no time series back ground, this is likely a simple question, but what is the relationship between "being able to" use an additive decomposition of a series into seasonal, trend ...
2
votes
0answers
101 views

Cyclostationary time series

http://en.wikipedia.org/wiki/Cyclostationary_process What are the methods in modelling and forecasting such time series? It is mentioned in the link above that there is a deterministic approach to ...
2
votes
0answers
174 views

Calculation of seasonal (annual) component of time-series: use of cross-validation?

I've been working for almost a year on electricity load forecasting in collaboration with some climate scientists, using temperature data obtained from models. Instead of using directly temperature ...
2
votes
1answer
585 views

Restricting a set of predictions to a range of values of non-negative numbers

I am not even sure how to even phrase this question so if anyone could help that would be great. I am analyzing facebook activity and I wish to predict a particular activity (comments, for instance). ...
1
vote
0answers
13 views

Product Demand Forecasting for Mutliple Products in Single Warehouse

I am working on a new project I haven't much experience with and was looking for insight on where to begin and methods to use. I am trying to produce a demand forecasting model (or perhaps sales ...
1
vote
0answers
14 views

What is the resulting distribution of a data set that was originally normally distributed but has been quantized and had all negative values removed?

I am trying to benchmark a seasonal forecasting model and calculate not just the point forecasts but the forecast densities from the model. To do this, I generated a simulated data set in the ...
1
vote
1answer
35 views

How to work with multi-step forecasting on differenced time series

I have a financial time series that I wish to make 5 step ahead (t+5) forecasts on. As the series is non-stationary, I have differenced the series. For every time step t, the response variable is ...
1
vote
0answers
57 views

Still seeing seasonal pattern in ACF plot after multiple differencing

I've seen a couple of questions asked here about seasonality "left over" (so to speak) after differencing like this and this, but unfortunately those answers don't help my situation. I have ~ 17000 ...
1
vote
0answers
17 views

Scenario Analysis with a GARCH model - conditional forecasts with hard restrictions on dependent variables?

Waggoner and Zha (1999), see reference below, developed an approach to produce conditional forecasts for VAR models with hard restrictions on the variables using Gibbs Sampling. As an example, they ...
1
vote
0answers
20 views

Fitting and forecasting a multivariate time series model (VAR) in R

I have some quarterly time series data for accumulated total public expenses and the total budget that I want to forecast. I also have subsets of the total public expenses, eg. health expenses and ...
1
vote
0answers
15 views

Suggestions for appropriate time series model , continuous outcome, time varying covariates

I am a dealing with a dataset which is as follows ...
1
vote
0answers
10 views

Is there a relation between the characteristic roots and the s.e of the arima coefficients?

in Forecasting: Principles and Practice there's a warning that inverse characteristic roots close to the unit circle may be numerically unstable, and the corresponding model will not be good for ...
1
vote
0answers
15 views

Covariance of prediction errors

I have an exercise to compute the covariance between the prediction errors, but I'm not sure if it is correct, this is the exercise; I have an AR(1) model, $y_t = \phi y_{t-1} + \epsilon_t$, where $\...
1
vote
0answers
30 views

How does BATS model work?

I am using BATS on a univariate time series model. I have observed strange behaviour. I have data from 2016 to till date (weekly level). If actual are considered from 2016 to 2019 May, I have used ...
1
vote
0answers
34 views

Is it possible to bootstrap a Diebold-Mariano test?

I am currently working on a small project where I want to use a (two-sided) 1-step ahead ($h=1$) Diebold Mariano test to compare forecast losses for different realized measures calculated on time-...
1
vote
0answers
19 views

Forecasting based on previous realizations

A given process has multiple variables moving to a target point. I can collect data of several realizations of this process. What forecasts methods exist for this? I'm familiar with exponential ...
1
vote
0answers
97 views

Does smoothed data work better for time series forecasting with LSTMs?

I am training a 3-layer LSTM on time series data ($10^6$ training samples) to predict the next point in the time series, where there is no seasonality and the time series has been made stationary (...
1
vote
0answers
28 views

Is it possible to reconcile forecasts that are not only at different levels of an organizational hierarchy, but also measured in different units?

Consider the following scenario: I have a top line revenue forecasts in dollars for each of my corporate divisions or business units. I have capacity forecasts for each of my regional manufacturing ...
1
vote
0answers
19 views

Narrowing down model for 2-independent variable time series forecasting

I've got a project I'd like to start working on and it roughly goes like this: I have past time series data for thousands of products that a company produces. There is a high weekly and yearly ...
1
vote
0answers
27 views

How to fit a regression model with ARIMA errors on the seasonally adjusted component of a time series (in R)?

I want to do these two things (combined) with a time series T: forecast the seasonally adjusted component of T (STL used for the decomposition) and "add back" the seasonality (I assume that the ...
1
vote
1answer
62 views

Is it possible to forecast multivariate time series using exponential smoothing equations? If yes what are those equations?

I know we can forecast univariate time series using different models of exponential smoothing , but am searching for whether same can be extended to multivariate time series and if yes what are those ...
1
vote
0answers
40 views

Adjustment of the forecast of a time series for the analysis of a system

I have a simulation model of a system which receives a forecast of a time series as input. In my scientific work I would like to examine how the performance of the simulation model behaves in relation ...
1
vote
0answers
41 views

Demand forecasting

I am forecasting number of phone calls (y) i ll be getting based on the products sold(x) and I am doing the following: (forecasted y) = (y/x averaged for past three weeks) * (forecasted x). 1. Please ...
1
vote
0answers
36 views

How to measure/rate the effect of a exogenous covariate in a ARIMAX Model?

I have an ARIMA model, I'm trying to figure out how much an external variable (exogenous covariate) could improve the forecast, so I need to "synthesize" a rate that tell me the usefulness (or impact) ...
1
vote
0answers
43 views

Product mix forecasting method

I have a main segment which includes different products. I have the percentages for each product and two year quarterly data. By using this information I want to forecast next years' percentages. I ...
1
vote
1answer
34 views

If I have a time series forecast density that is bi-modal, does that mean that my data is heteroscedastic?

The title pretty much explains it already: If I have enough data points that I can plot my entire forecast density and it ends up looking like this, does it mean that it is heteroscedastic and I ...
1
vote
0answers
30 views

Is it correct to make a conclusion as to whether a model is best for weekly or daily forecasting by comparing the root mean square errors?

I am performing daily and weekly forecasts for 28 days and 4 weeks respectively. Once I have used the same model to obtain the respective forecasts an root mean square errors (RMSE), I will like to ...
1
vote
0answers
41 views

Missing as opposed to non existent data in time-series forecasting

Suppose you have a set of observations that occur at regular intervals in time, but containing regular gaps during which there is no data, not because it is hidden or missing, but because the ...
1
vote
0answers
19 views

Incorporate recent drop in number of units sold in a forecast using exponential smoothing

I'm trying to generate a one-year forecast for the number of units sold by a retail company. I'm using monthly data from 2017 and 2018. The forecast is for 2019, and I'm using the data from the months ...
1
vote
0answers
43 views

How to train an LSTM model on multiple single-variable time-series data?

I am quite new to the field. I am working on a problem involving time-series forecasting of single variable time-series. Data is collected from the pressure sensor on a patient in hospital. Time ...
1
vote
0answers
12 views

Does forecast error variance decomposition in which the response variable predominately explains itself imply the model is incorrectly specified?

So I have set up a six variable VAR model in the hope of explain natural gas prices and performed forecast error variance decomposition, however the response variable (natural gas prices) explains ...
1
vote
0answers
141 views

Neural Network regression on time series

I want to predict the trend values of a time serie [Y] based on the effect of other 10 input variables which can also have interaction. Since the combination of interaction between the inputs is ...
1
vote
0answers
18 views

Future event prediction methodology

I have a data set such that each data point is an "event" with features $x_1, x_2, \dots, x_n$ and the year of its occurence $y$. I want to train a forecasting model that predicts when an event of ...
1
vote
2answers
111 views

Forecasting daily data with zeros in Python

I'm currently testing some forecasts on daily sales quantities. However, out of ~2000 observations I have 16 zeros. How should I approach this? It's mainly Sundays and holidays that holds zero as ...
1
vote
1answer
151 views

Forecasting recurring orders for an online subscription business using Facebook Prophet and R

I am analyzing data from a subscription model, in which a customer must pay a recurring price at a regular interval (30 days) for access to the product. EDIT -> Direct link to daily data: https://...