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
0
votes
0answers
17 views

Comparison using MASE,MAPE for aggregated data with different points of forecast

Despite the fact that it's necessary to analyze the data first, is it possible to compare accuracies (MAPE/MASE) for differents points of forecast from aggregated data (flow, as in Silvestrini and ...
0
votes
0answers
14 views

Exactly how are cyclical components computed?

So suppose we have some sort of a time series model. y_t = trend_t + cyclical_t + x_t + epsilon_t So, I'm interested in obtaining the seasonal component. Here "x_t" refers to other potential ...
5
votes
3answers
470 views

For a time series problem, Why is it preferrable to use a time series model over a model without an explicit time component?

High Level Question: What is the advantage of modeling data as time series? For a problem involving (mutlivarate) time series data, why is it useful to model the problem as a time series problem, <...
0
votes
0answers
28 views

Forecasting a multivariate time series with few observations

I am trying to forecast the number of confirmed cases for several days (1, 3, a week) of a virus with the following data: ...
1
vote
1answer
47 views

How choose a proper ARIMA model?

I am doing my project on forecasting and I have to use the ARIMA for it. I have tried but still unable to identify which ARIMA model is appropriate for my data set? Either to use ARIMA or SARIMA. ...
1
vote
1answer
68 views

Time Series Forecasting Right Metric

I'm doing a time series forecasting using Exponential Weighted Moving Average, as a baseline model. I'm wondering on what would be the best metric to use if I have ...
0
votes
0answers
18 views

How can i apply forecasting model in R to get the forecast result of sales (daily) against product/item?

I know to make time-series we need two columns x-axis contains(date may be year,month or daily basis) and y-axis contains(sales,price,quantity or demand) w.r.t dataset you're working on. But in my ...
1
vote
0answers
14 views

Curve Fitting Metrics: Mean Percent Difference

I recently discovered my colleague (not a mathematician) was evaluating their experimental regression analyses by reporting the mean percent difference of each estimated output (from their fitted ...
0
votes
0answers
11 views

cwRMSE, ewRMSE calculation for forecast accuracy

I have one year worth of data with three columns: wind power forecast, wind fact power production, wind installed capacity. And this three value is available for each hour of the examined year. I ...
0
votes
0answers
13 views

RNN does not learn simple time series [duplicate]

I can't get a RNN to learn a simple linear sequence, broken into 90 batches of 10 steps each I would expect that it should totally overfit the training sequence. Instead, it does not learn (high loss)...
0
votes
0answers
56 views

Seasonal Arimax differencing Issue

I have weekly data of yearly seasonality around 3.5 years. By using default seasonal test ocsb or ch test in python pmdarima it is not able to give right D differencing which is resulting in higher ...
1
vote
1answer
38 views

Scoring rules for time series data

I have found quite a lot of articles about scoring rules that seem to first work out theorems and proofs for scoring rules in an iid setting, after which they proceed to apply them to some time series ...
0
votes
0answers
14 views

Lack of accuracy for sales forecasting [duplicate]

I'm an intern in a company that sells about 900 products. We are trying to forecast our sales for the next year. I already have the monthly data for the 3 previous years, cleaned it, and analysed ...
0
votes
1answer
80 views

How can I forecast with multiple time series sampled at different frequencies?

I am attempting to build a time series model that can predict order volumes for a single firm in the trucking industry. I have time series data on the firm's order volumes. This data is monthly data. ...
0
votes
1answer
34 views

Modeling with seasonally adjusted series and BoxCox

I have time series with daily data. This time series have frequency 7. Before I start with modeling first I made seasonal adjusted series with STL decomposition (from forecast package). So next step ...
0
votes
3answers
56 views

Is there any Forecasting algorithm or way to forecast the daily data available only on working days only(i.e Mon to Fri)?

Since My data frequency is daily but data is not available on Weekends( Sat and Sun) and Holidays.Therefore nearly 30-40 % data is missing with sequential time series. So I don't know how to deal with ...
1
vote
1answer
35 views

Scaling SARIMA to forecast on thousands of series

Currently, I am building out different models for forecasting. SARIMA usually does a great job with the series I am forecasting. Currently, I only have ~100 series to forecast (each series is between ...
0
votes
0answers
13 views

How to Account for Decreasing Trends in R Forecast (Asymptotic Prediction Functions?)

I am doing forecasts for US counties on a few economic criteria. I am using the "forecast" package in R. How do you set up the forecast so that the effect of the trend decreases as it approaches a ...
0
votes
0answers
30 views

Forecast the proportion of a product

my question is the following: I have to forecast the proportion of the sales of a product. For example: For product 17503 there are four types of categories A, B, C and D. The total demand of the ...
3
votes
1answer
54 views

Backshift Operator: Is it well-defined?

I have seen the backshift operator $B$ defined as $Y_{t-1} = BY_t$ in class. But I don't understand why this is a reasonable thing to do. Does the backshift operator exist for all discrete time ...
1
vote
1answer
31 views

Create auto regressive regressors in R (extract from auto.arima) [closed]

I have time series with daily data with, this series have 7 frequency. I used auto.arima in order to determine regressors. This function suggest me to use five regressor ar1,ar2,ar3,sar1 and sar2.You ...
0
votes
1answer
32 views

forecast criterion

I am doing out of sample forecast for my daily exchange rate data. Here I am using different models like ARIMA(0,1,3), ARCH(3), GARCH(1,1), EGARCH(1,1) and TARCH(1,1) with 3 distributions (normal,t ...
1
vote
1answer
45 views

Questions re Time Series Forecasting in R

I am attempting to build a time series model that can predict order volumes for a single firm in the trucking industry. I have time series data on the firm's order volumes. I expect also to have ...
0
votes
0answers
15 views

Defining predictive density of a time series

Assume predictive density of a time series is Gaussian. So when we define the variance term of the distribution, should we use the conditional variance of the forecast errors or unconditional variance ...
1
vote
1answer
35 views

Predict change in variable

Probably this is easy to answer, but let me formulate the question: If we have a variable $Y_t$ measured over time and cross-sectionally, and we calculate the change of this variable from $t-1$ to $t$,...
0
votes
0answers
51 views

ACF and PACF with daily data

I am modeling with daily time series and some forecasting models from forecast package.But at the beginning I have some problem with time series.Namely I want to try to explain ACF and PACF but I can'...
0
votes
0answers
21 views

How to estimate the predition power of x(t) on y(t)?

Suppose I have two time series: y(t) and x(t), with y(t) the time series I want to predict and x(t) as the input for the prediction. My question is straightforward. How do I know if x(t) has the ...
0
votes
0answers
16 views

many datasets with multivariable continuous time series

I have many data-sets, each one have many variables (Time, X1, X2,..,Xn, Y) and Time variable is continuous [0-1]. the number of observation in each data-set is not equal and not synchronized in time: ...
1
vote
1answer
29 views

What is the coefficients of determination of prediction?

I have never seen this term mentioned before. Yet this study uses it: https://www.econstor.eu/bitstream/10419/204328/1/ifro-wp-2011-12.pdf Is it any different than the typical R^2, i.e. ...
0
votes
0answers
22 views

Modelling a race

If we imagine an outdoor race with two obstacles: If the participant fails an obstacle attempt they exit the race Historical data shows that about 50% of participants will fail each obstacle That ...
0
votes
1answer
31 views

Forecast survey response rate

I am new to Bayesian forecasting and hope you can help me get started with this problem: I need to forecast the likely survey response rate to a paid-for survey Background information: Each person ...
0
votes
0answers
36 views

Forecasting Prediction in R

Currently, I have a dataset which includes the price of electricity every hour and the demand of electricity every hour. I have then another dataset that only has the demand for electricity every hour ...
0
votes
0answers
21 views

The point of VAR conditional forecasts

I wonder what's the point of making conditional forecasts in VARs as in Waggoner, Zha (1998) in favor of forecasting via VARX. What makes it especially dubious is the fact that VAR is estimated step ...
2
votes
1answer
84 views

VAR models vs univariate models

Suppose I know the true DGP is a VAR(1) process. Instead of fitting a VAR model, I can still fit univariate ARMA models to each of its components. Does anyone know whether it will result in biased ...
1
vote
2answers
63 views

Is there a guide for when to implement time series techniques?

I am interested in getting a better sense as to when to use time series techniques. Let's say you have a data set with units sold as the response. Your goal is to predict units sold on any given ...
0
votes
1answer
39 views

What is the difference between using a time series model and using i.e the naïve approach for forecasting?

I was reading about forecasting at Wikipedia: Forecasting and I noticed that in the publication they separate the Naïve, Average and Drift approach from the Time series methods (which involve AR, MA, ...
1
vote
1answer
25 views

Distribution that acts like Poisson/NegBin for small means and like a Normal distribution for large means?

I want to generate a full density probabilistic forecasting model, where I don't know a priori whether the time series I want to model are intermittent or dense. In both cases, the time series is a ...
1
vote
0answers
20 views

Interpreting Ljung-Box white-noise test p-value

Good evening all, I am having some trouble understanding the Ljung-Box white-noise test p-value from SAS Forecast. So there are lags where the p-value exceeds 0.05, meaning that we fail to reject the ...
1
vote
0answers
18 views

Predictions on transformed series post intervention analysis

I have taken this logged data and performed an intervention analysis: ...
1
vote
1answer
90 views

Specifying seasonality in a grouped ARIMA model with fable

I'm using Rob Hyndman's groovy new tidyverts family of packages (the replacement for forecast). I was just wondering how you'd specify that the data is seasonal, especially in the presence of groups. ...
0
votes
0answers
23 views

What kind of method to use to predict multiple time-series with missing data points and of different lengths

I have to create a model to predict future sales of different restaurants to use in investment decisions. For about 1000 restaurants, I have the following data: Weekly sales (split out over product ...
0
votes
0answers
58 views

Selection Of Model---prediction of cpu usage

Currently I am working on a project and was hoping to ask this question as a sanity check as I am still very new to this area. Currently I am collecting CPU usage values for machines at a 1s interval ...
0
votes
0answers
32 views

Forecasting panel data

I am trying to forecast my dependent variable 9 periods ahead, having a history of 25 years. I have panel data with 34 countries and 25 years for each country – 850 observations in total. Currently ...
2
votes
0answers
82 views

Regarding Hyndman's approach to estimating prediction intervals for forecasts generated by neural networks

I'm currently looking for ways to estimate prediction intervals from an LSTM generated forecast. Several advanced methods are suggested in the literature (e.g. SQF-RNN), but as a first pass, I'm ...
0
votes
0answers
21 views

Forecast package in R

I have one question which is maybe very simple. So my question is does models from forecast package in R (e.g auto.arima,ets,tbats,nnetar etc) are machine learning models or not?
0
votes
1answer
40 views

Akaike information criterion, long time series, and overfitting ARIMA?

I'm trying to forecast a stock index with daily data from 1990 to today (over 7000 data points) with ARIMA, after correlogram, information criterion (prioritizing Akaike) and auto selection (either ...
0
votes
0answers
65 views

How do I interpret parameter estimates in additive exponential smoothing?

I am trying doing a course on time series forecasting and did a forecast for an airport arrival on SAS forecast studio. Additive exponential smoothing is used for my choice of forecasting. How do I ...
0
votes
0answers
71 views

Forecasting R Package Downloads

Disclaimer My ramble posed below may be considered off-topic for CV, but I thought I would at least try to post it here as I am curious as to others' thoughts/opinions, because I have not encountered ...
0
votes
0answers
14 views

Forcasting with only total sale of product?

is it possible to make a forecast when you only have the total sale (of last year) per product variant? I would like to make a forecast for the next year 2021. So for example, if last year's sale per ...
2
votes
1answer
57 views

Is it appropriate to select an ARIMA model without having statistical significance of all the parameters?

I am trying to identify an ARIMA model for the following time series: According to the ADF test, it is stationary (p-value = 0.0144). When I use the ACF and PACF, both show correlation without a ...

1
4 5
6
7 8
62