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
1
vote
0answers
36 views

Have log returns series almost always conditional mean zero? I presume no

I'm analyzing S&P500 stocks daily log-returns on the 505 time series of the biggest companies in the USA between 2014-01-01 and 2019-12-01. My task was to identify the ARMA-GARCH model of them. ...
0
votes
0answers
15 views

How does clustering will affect the MAPE and RMSE?

MAPE and RMSE are two very popular techniques to calculate the error. Now assume I have time series and cluster them to K clusters. This might reduce the training time when we are using the ...
0
votes
0answers
14 views

Why do test set predictions perform far better than a recursive forecast - time series forecast

I've been dealing with a LSTM stock forecaster, and I've been looking at articles like 1, 2. I know that the models are very likely overfitted, but nonetheless, the test set predictions are quite ...
2
votes
1answer
22 views

Higher RMSE lower MAPE

I have a time series model that forecast next K days. For example when I forecast next 50 days my MAPE is 20.3% and RMSE is 2943 and when I forecast next 200 days is the MAPE is 10.25 % but RMSE is ...
4
votes
1answer
1k views

Identifying lagged effects / Distributed Lag Model

I would like to create a linear distributed lag model in order to do some forecast and also being able to interpret the results. Unfortunately I'm a bit confused with the process I should follow....
2
votes
1answer
27 views

General exponential smoothing to linear functions of past observations

I am just trying to derive an equation in "Forecasting with Exponential Smoothing" page 36 section 3.2. I am given the following $\hat{y}_{t|t-1} = \textbf{w}'x_{t-1}$ $\epsilon_{t} = y_t - \hat{y}...
6
votes
4answers
1k views

Choice of time-series model for store sales prediction

I have a data set of weekly sales for a range of stores (all belonging to one company). I am trying to predict weekly/monthly use of several ingredients in the individual stores. The choice for what ...
1
vote
1answer
820 views

Which model to use between VAR and VECM for the following problems (conditions)?

I have three variables (monthly for 25 years) including wages (e.g. skilled and unskilled) and food price (P). I am interested to see if there any relationship exist between them, either short or long ...
1
vote
1answer
121 views

Combining Forecasts for Discrete Outcomes

Suppose you have $n$ forecasts for an event which can have discrete outcomes, for example $X$, $Y$ and $Z$. Let forecast $i$ give the probabilty of each event occuring as $x_i$, $y_i$ and $z_i$ ($x_i+...
0
votes
0answers
17 views

How to make StatsModels ARIMA more accurate?

I'm working on a big data project for my school project. My dataset looks like this: https://www.kaggle.com/umar47/usd-try I've translated column names to English to work smoothly. New column names ...
7
votes
4answers
203 views

Is it a valid claim, that by differencing a time series, it loses its memory, and as a result its predictive power?

Marcos Lopez de Prado seems to be a well known and renowned machine learning expert in the field of finance. I am very far from his level, as have not yet finished my PhD in economics, and only have ...
5
votes
3answers
155 views

Forecasting/predicting total sum of donations (following GLM with poisson family and log link)

I am trying to predict the total sum of donations that Monica will receive on https://www.gofundme.com/f/stop-stack-overflow-from-defaming-its-users/ I copied the data and summed for all days the ...
4
votes
1answer
486 views

Model selection and estimation for pseudo out-of-sample forecasting

I have quarterly data on inflation from 1990 Quartal 1 to 2016 Quartal 3. If I want to perform the pseudo out-of-sample forecasting one quarter ahead with an autoregressive function, do I have to ...
1
vote
1answer
132 views

How can I ensure that my backcasting values are positive in R?

Is there any option in R that could allow me to obtain just positive values in my forecast? I applied the following code for backcasting public expenditure in health quarterly time-series, but I ...
3
votes
1answer
485 views

Trending time series data normalization for Deep Learning

I'm replicating following article Financial Time Series Prediction using Deep Learning and I'm stuck with data normalization. In chapter 5.1 in the second paragraph in the last sentense the authors ...
1
vote
2answers
45 views

Forecasting using regression model

I am regressing gross sales against two regressors X1 and X2, and have a linear regression model with me. I want to use this model to get forecasts far out into the future where the values of X1 and ...
1
vote
0answers
16 views

Can you recursively forecast one series with two series?

My question is probably very elementary but I haven't been able to find an explanation of recursive forecasting that I fully understand. I've read a journal article that seemed to recursively ...
1
vote
2answers
382 views

Dealing with missing data in Time Series or non-constant time intervals for forecasting in R (ARIMA, Holt Winters, Theta)

I have a time series of sensor data from a machine. This machine is sometimes moved and thus there are big chunks of missing data, here is a plot of the data points: My goal is to try to start ...
0
votes
1answer
852 views

Simulation and mathematical notation for ARIMA(0,1,1) with drift

I am attempting to write the mathematical model for and also simulate an MA(1) process that has drift (in R). I have referenced ARIMA (0,1,1) or (0,1,0) - or something else?, Simulation of forecasted ...
2
votes
1answer
140 views

Predicting water levels based on rainfall stats

I am curious if R or any other open source code can deal with forecasting changes in water elevation based on a predicted/forecasted value of rain. I have a ton of data that shows water elevations (...
0
votes
0answers
27 views

Forecasting with no seasonality

I have a transactions data frame and a promotions data frame. And I want to perform a forecast. The problem is that I can't tell if my data presents seasonality or not. I mean the sales per week looks ...
1
vote
1answer
38 views

How do we forecast using 3 point moving average?

X<- c(3,6,8,10,6,5) If I want to forecast using 3point moving average I use ma(X,3) from forecast package So this is going to give a series of smoothed average. If I want to forecast further 2 ...
0
votes
1answer
152 views

Auto ARIMA model summary interpretation in r

I am new to time series and am trying to forecast a data series in r; which has weekly data. I have a few questions related to the same: While trying to use auto.arima() model, it shows the optimum ...
1
vote
2answers
168 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
31 views

Correlation between features in time-series

This is a technical/conceptual question. I am not sure if this is the right place to ask. If not, please let me know, I will change it. Question: I have some time series data with 12 room ...
1
vote
1answer
48 views

Why do the regression residuals from a regression model with ARIMA errors differ from residuals from a linear regression model?

Let’s start loading fpp3 package (https://github.com/robjhyndman/fpp3-package) and the US consumption expenditure dataset (https://rdrr.io/cran/fpp3/man/us_change.html) ...
3
votes
2answers
843 views

Can I overfit an ARIMA model?

I am using the forecast package and the auto.arima function. This function tries different arima model with different p and q ...
6
votes
1answer
944 views

forecast::auto.arima() is not returning a model with a differencing parameter when it should

I'm experiencing an issue in which it seems forecast::auto.arima() isn't returning a model with a differencing parameter when it should. Read through my reproducible example to arrive at the question. ...
1
vote
1answer
12 views

Scaling the MAE by the mean of non zero points for intermittent data

I am currently trying to find a way of scaling the MAE for my intermittent data. The data is always greater than 0 and is intermittent, with long periods of zeros. I have read a few papers that ...
1
vote
0answers
45 views

“Back-casting” a Time Series

The problem I have is that i have a series of data (between 2000-2010) and i have another series (independant variable) which is available between 1980 and 2010. I need to backcast the value of the ...
1
vote
1answer
46 views

Recursive or direct forecasting used in forecast/predict() in stats models

I am working on a time series project. I have an hourly series and I have to forecast the 24 next hours. I am facing a problem with understanding how both the stats models forecast() and predict() ...
3
votes
1answer
128 views

Forecast a staircase-like time series

I am working on this problem for my research. The attached time series represents the memory usage of an application over time. As you can imagine, the memory usage steps up randomly every few days. ...
2
votes
3answers
810 views

XGboost for Time series - using lag of target variables

I'm trying to make a time series forecast using XGBoost. I have already added many time related variables - day_of_week, month, week_of_month, holiday. I want to add lagged values of target variable ...
5
votes
1answer
782 views

How to specify when a level shift begins and ends or in the case of data series with multiple level shifts how to id when one level shift beings/ends?

I am working on forecasting airport delays the data looks like this It looks like there is a structural break around 2004 where theres a huge increase and then a huge decrease around 2009. I am ...
1
vote
1answer
41 views

How to know /guess which series(out of 100) will give better forecast before applying any time series model and without plotting each series?

I have More than 100 variables which are to be forecast. But before applying any time series model and plotting series, How can I guess that a particular series may have a higher chance of getting ...
2
votes
1answer
38 views

Is it necessary to remove Seasonality while time series forecasting using ML methods ? Can't model learn it on itself?

I think ML model can learn from seasonal variations also. But if we remove seasonal variations, model & add it back, then essentially, we will end up dividing learning into : 'seasonal variations ...
0
votes
1answer
6 views

What type of panel data model to run for forecasting on a site level basis?

I am trying to forecast monthly energy volume on a site-level basis (around 2,000 individual sites). I have monthly data for each site for at least two years. I also have attributes such as square ...
2
votes
0answers
682 views

Daily data forecast: How to specify day of week and month of the year seasonality in SAS [closed]

I have daily data for 2 years starting from jan1 2014 till december 31 2015. I want to forecast for next 365 days using this data set. I am using below code. ...
1
vote
0answers
70 views

After making an adjustment to the forecast, should I also adjust the prediction interval (& how)?

I want this to be a general question as it may help others in the future but I will give the specifics of what I'm doing. I am producing forecasts for many time series with different models. It is ...
0
votes
0answers
152 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
19 views

Is Box-Jenkins approach to time-series prediction and forecasting similar to Unobserved Components models approach?

How I understand the Box-Jenkins Method in a nut-shell is that a time-series model has signals that can be identified by weighting its own past lagged values, or weighting its owned past errors or ...
4
votes
4answers
955 views

High-Frequency Time-Series Forecast With A Lower Bound

I am helping a friend with a data project. He's interested in building a canary-in-the-coal-mine alert system for his website which tells him when the number of users dips below some critical lower ...
6
votes
3answers
10k views

Performance evaluation of auto.arima in R and UCM on one dataset

I started evaluating and comparing some methods in forecasting. I used Price of dozen eggs in US, 1900–1993, in constant dollars in the R software FMA package. I held out the last 10 years for ...
0
votes
1answer
19 views

RNN model for predicting room temperatures

I am currently doing a project in Machine Learning where I am trying to predict the temperature of a room in future. I have a 1-year dataset of a house with 12 rooms. Data is collected at 10 min ...
1
vote
0answers
22 views

Interval and density forecast in R with both heteroskedasticity and non-normality in time-series data

We tried to get both an interval and density forecast based on time-series data, which we found to be both non-normal and heteroskedastic, in R. We know that for non-normality, forecasts can be ...
0
votes
1answer
128 views

How to solve or choose the smoothing parameter phi in solving for the Nonlinear trend exponential smoothing?

In forecasting, to solving for the nonlinear trend exponential smoothing can you just choose any value of ϕ or is there a way to solve for it?
0
votes
0answers
21 views

Use R forecast::arfima to forecast anti-persistent series - REPOST - more nicely formatted

I'm trying to use the R forecast package to forecast an anti-persistent time-series (assumed to be an ARFIMA(0, d, 0) series, with d somewhat negative, e.g. d = -0.25). The forecast::arfima function ...
0
votes
0answers
13 views

Use R forecast::arfima to forecast anti-persistent series [duplicate]

I'm trying to use the R forecast package to forecast an anti-persistent time-series (assumed to be an ARFIMA(0, d, 0) series, with d somewhat negative, e.g. d = -0.25). The forecast::arfima function ...
1
vote
1answer
3k views

Random walk out of sample forecasting

I'm having some problems in writing down in R the out-of-sample forecasting with a Random Walk. I have a multivariate time series (y) and I want to estimate the out of sample forecasting (y(t+k)-y^(t+...
8
votes
1answer
2k views

How to compare forecasting methods?

I have several intermittent data. Based on those data, I would like to compare several forecasting methods (Exponential Smoothing, Moving Average, Croston, and Syntetos-Boylan), and decide whether ...