Questions tagged [forecasting]

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

1,030 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
0
votes
0answers
1k views

Time Series Analysis vs Linear Regression for GDP data?

I am trying to build a simple econometrics model that uses urban population, total factor productivity among other things to predict future GDP of a country. First I approached the problem by using ...
0
votes
1answer
69 views

How to choose predictors to forecast?

I have a data sheet includes 66 variables. And explanation variable is seasonal. How to choose the predictors and which model to use? Is there any basic steps?
0
votes
0answers
645 views

Log transformed MAE to original value

In order to evaluate the forecast accuracy of a model I'm using a step wise cross validation to get a MAE value and use that again to calculate the MASE. As part of the model specification the data ...
0
votes
0answers
541 views

Mimicking seasonaldummy with fourier in Arima model

I'm trying to forecast data that has an hourly and weekly pattern. The model I made using predictors created using seasonaldummy does a nice job of picking up the hourly weekly pattern, but it takes ...
0
votes
0answers
195 views

estimating effect size with sMAPE in published results

I'm struggling to get the concept of effect size in the published forecasting literature. Most common metric that is used is the symmetric Mean Absolute Percentage Error (sMAPE). For instance see ...
0
votes
0answers
407 views

Seasonality and trend window in the Forecast functions of R

I have time-series power consumption data for one month. The data is sampled at minutes frequency. Thus, for each day I have 1440 observations and for the month (30 days) I have 4320 observations. On ...
0
votes
0answers
137 views

Irregular seasonality defined as white noise?

I've got data of which I think it has a seasonality. My data has a peak in july/august and one in december. I have only data of 2014 and 2015, but in both of the cases this is happening. (See my graph)...
0
votes
1answer
96 views

Calculate Forecast Error: Different ways using the mean?

Example: I've got an forecast with 2000 values. Let's say they are for one year. I can group my values into months. Every month can include a different number of single values. (JAN with 200 values + ...
0
votes
0answers
67 views

Violating use of information in time-series forecasting

I am trying to forecast stock market returns using a rolling time frame. I want to fit a model on a 20 (trading-) day period and then predict one step ahead - the ...
0
votes
0answers
35 views

Accuracy of time series predicton

I have two time series - actual and predicted. They both can be positive or negative, can jump or remain constant, one can be positive other can be negative - basically any combination is possible ...
0
votes
0answers
142 views

(S)ARIMA — Hints with Time Series

I am a beginner in time series analysis and I would like discuss a couple of numerical examples here implemented in R. I am reading some interesting books, but I also need some expert advice to get ...
0
votes
0answers
2k views

Compare forecast models accuracy

I have a time series of number of visitors of an website for two years. I have to do the forecast of the number of visitors for the next semestre. To do so, I used three forecast models: ARIMA, ...
0
votes
1answer
77 views

Linear Regression Model in R - Which variables should I use?

I would like to fit a linear regression model in R for predicting motorbike prices. My dataset has 13 variables, including number of kilometers driven, colour, month of the first registration, etc. ...
0
votes
1answer
72 views

crossvalidation for forecasting sales

My objective is to predict the sales 6 weeks in advance. I have data that from 01-Jan-2013 to 31-June-2015. I am supposed to predict the sales from 01-Aug-2015 to 17-Sept-2015 using machine learning. ...
0
votes
0answers
1k views

Sales forecasting - using historical data in conjunction with new variables

Yes I face the age-old problem of sales forecasting for a large enough company. Mostly to determine our staffing needs for various functions. So I'm only really interested in aggregate data, not ...
0
votes
0answers
63 views

Non-negative forecasts with missing data and clustering

I have a data set of deposits and withdrawals from bank locations, so each record includes a bank identifier, date stamp, number of deposits, and number of withdrawals. I have included reproducible ...
0
votes
0answers
566 views

Can ARIMA be used to forecast trend in time series data?

I am new to ARIMA. I have a time series data that has a negative trend.I need to predict its value for the upcoming time period. I know that one of the steps in ARIMA is to de-trend data through ...
0
votes
0answers
74 views

Forecasting error from GLS estimator

As well known, $\text{Var}(\beta_{gls})\leqslant \text{Var}(\beta_{ols})$. From this, we can conjecture that the following inequality also holds: $$\text{E}(y_{T+1}-X_{T}\beta_{gls}|\iota(T))^2 \...
0
votes
0answers
55 views

Strategies for Prediction : Forecasting Production

As an example : I have data for production of a plant for a period of 2 years. Data set: Jan 2013-Jan 2015 I have created a machine learning model to predict production. The sales are to be ...
0
votes
0answers
132 views

How to compare forecast performance of two subsamples?

I need to compare forecasting performance of two subsamples. I need to evaluate whether a change that was introduced improved the forecasting performance i.e., compare the forecasting performance ...
0
votes
0answers
42 views

RandomForest one-sided difference in forecasts

I have 1,100 entities (stores) across 80 months with 45 different variables, and I'm trying to predict the occurence of an event (this is a binary result) for each store. For example: ...
0
votes
1answer
50 views

Advice on predicting continuous dependent variable

My challenge: maximize $R^2$ on an out of sample data set. Constraints: Continuous dependent variable with negative values Over 150 variables with no information about them Some of these ...
0
votes
0answers
29 views

Using t-statistic to calculate confidence limit from pcr forecast and forecast error

I have come across a usage of the t-statistic that I don't understand. It comes from a government panel. It is work related, and I can't provide the original reference, but I do want to try to ...
0
votes
0answers
255 views

Constant-output Markov chain in time-series prediction

Suppose a Markov chain with two discrete states $A$ and $B$. The probability of moving from $A$ to $B$ is $0.1$ and the probability of moving from $A$ to $A$ is $0.9$. Similarly, $B$ to $B$ has ...
0
votes
0answers
862 views

Should I ignore negative prediction values?

I have the following time series of count data: ...
0
votes
0answers
189 views

How to predict or forecast in transfer function model?

Is there any way to predict a transfer function model by using predict() (or else) in R? I'm searching the package to do forecasting in transfer function model, but couldn't find one.
0
votes
0answers
57 views

Forecasting daily subscriptions: which method should I use?

I am interested in predicting the data for a day, based on the data given from the 14 previous days. The data I am working with is the number of subscriptions to a website per day. Each day, the ...
0
votes
0answers
68 views

Hierarchy predictive top down approach

I'm having a problem with using a hierarchical top down forecasting approach. According to my understanding, when I split an aggregated value on the levels below it, I have to know the percentages ...
0
votes
0answers
156 views

Proc UCM Forecast Series

I'm forecasting a data series with one time dependent variable (GDP) and one 0 1 time indicator "Flag" (0 starting at February 2014, 1 before that). When I use ...
0
votes
0answers
40 views

What's the nowcasting “bible”?

Is there an accepted best text about nowcasting that you would recommend for someone getting into the field?
0
votes
0answers
882 views

Time series forecasting using SVM

I am trying to set up a Python code for forecasting a time series, using SVM libraries of scikit-learn. My data contains $X$ values at a day interval for the last one years, and I need to predict $y$ ...
0
votes
1answer
101 views

Forecasting Prediction Accuracy

Out of 4 error paramters which one is best for evaluating prediction accuracy? Average error Mean absolute error Mean squared error Mean absolute % error why?
0
votes
0answers
235 views

Improving forecasting output obtained from Winter, ARIMA and TBATS method

I am trying to forecast commodity price for next year. I have collected and plotted monthly average prices from last 10 years.Plot has been attached. I used Holt's-Winter method on prices till 2014 ...
0
votes
0answers
552 views

Timeseries forecasting (Cointegration)

I am trying to forecast commodity price fluctuations in a small dataset. The data I am using is here . Does my data have seasonality and Trend? Can someone explain me how to decide that? If my data ...
0
votes
0answers
1k views

Questionable Output from Time Series Forecast Using MSTS and TBATS from R forecast package

Using historical daily order totals, I'm wanting to forecast the totals of the next 7 days. It's known in my field that these totals fall subject to weekly and yearly seasonal trends. Called ...
0
votes
0answers
273 views

Multivariate stochastic time series forecasting

I have a multivariate time series like this ...
0
votes
0answers
559 views

Better forecast on seasonal type and lessthan 1 year of data

I have a client which started on december 2014 and they are only capable of sending their sales during middle and last day of the month. I used exponential smoothing to get their forecast sales. The ...
0
votes
0answers
2k views

Forecasting in r using ets() of forecast package..seasonality and trend not detected

I have tried forecasting in R using ets(). I let ets choose the best model for my data. The problem is i observed that eventhough the data shows an increasing trend and exhibits seasonality, ets is ...
0
votes
0answers
363 views

General forecasting formula for ARIMA(p,d,q)(P,D,Q)s

what is general forecasting equation for sARIMA(p,d,q)(P,D,Q)s.? I wrote this equation, can someone confirm if it is a correct one? $\overline{y}_{t+m}=\frac{ (\varphi_{1}y_{t} + \varphi_{2}y_{t-1}+....
0
votes
1answer
228 views

General forecasting equation for ARIMA(p,d,q)(P,D,Q)s

what is general forecasting equation for ARIMA(p,d,q)(P,D,Q)s.? I wrote this equation, can someone confirm if it is a correct one? If not, can someone correct it? Thank you in advance! $\overline{...
0
votes
0answers
857 views

autocorrelation in evaluating time series forecasts

I'm having some trouble wrapping my head around whether using Holt-Winters ETS or an ARIMA model for forecasting sales figures (which are highly seasonal). I'm been using R and the Forecast package --...
0
votes
0answers
420 views

Formula behind forecast in R

Can anyone tell me the formula behind the forecast function in R? Preferably in the form easily understood by mathematicians (e.g x_t, θ etc) Here is my code in ...
0
votes
1answer
37 views

Can I use this equation for prediction?

I've got a question. Below you see a graph which shows the regression equation between construction activities in the private sector (X axis) in £bn and the total amount of all construction activities ...
0
votes
0answers
197 views

Adding predictor variables and/ or systematic judgement to time series forecasts

I have a ways to go with my forecasting general education --- but I'm doing a seasonal time-series forecast for predicting sales order volumes. It's mostly software sales, which does have a ...
0
votes
0answers
164 views

What is the source of nonstationarity in this VAR model?

I am trying to forecast a VAR model, which consists out of 5 variables with a monthly frequency. The problem is that the VAR model produces an unstable forecast and I am not sure what the source of ...
0
votes
0answers
41 views

Have a data set for 3 consecutive days. What are my options?

Let's say I have a set regarding the transportation methods(Eg: car, bus, train) used for three consecutive days b y $n$ number of people. For simplicity let us assume that everyone use only one type ...
0
votes
1answer
93 views

Very different Neural Network test errors for same architecture

So I'm doing a time series prediction, and assessing the capability of the ANN to predict that time series. I am using Matlab's neural network toolbox functions, and the training parameters are the ...
0
votes
0answers
251 views

forecasting for data excluding holiday dummies

I used tbats to fit a model to a set of 3 years of historic data for daily number of shipments moved by a trucking company. my data included double seasonality so I used tbats. However, tbats did not ...
0
votes
0answers
1k views

Different fitting models using auto arima and tbats

I have one year of daily data for forecasting. while using auto.arima to find the best fit model, it gives me ARIMA(3,1,3). However, when I used tbats to find the best fit model, it gave me the ...
0
votes
0answers
225 views

Double Seasonal Holt winter method using dshw

I have a two weeks data set which have intraday and intraweek cycles so I decided to use dshw in r. Although it gave me a pretty good MAE and RMSE, when I wanted to see SSE, it showed me a null value. ...