Questions tagged [forecast-combination]

The process of combining different forecasts to get a better resulting forecast than any of the constituents. Simple forecast averages are often found to outperform individual forecasts in practice.

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

Forecast combination with nonstationary time series

Suppose I have a non-stationary time series and have obtained forecasts using various methods such as ARIMA, ETS, Theta etc. I want to find a weighted combination of these forecasts. I found in the ...
1
vote
0answers
15 views

How to combine observational and experimental data?

I’m trying to figure out the effects of system changes on user long-term revenue (over a 12-month period, say) for an online platform. I have a lot of observational data, so I fitted a model that ...
0
votes
0answers
18 views

Multivariate Time series forecasting- Statistical methods

I was trying to forecast the truck numbers required at each distribution location...for that I was forecasting the shipments(number of units) at each location and dividing it by a factor to get the ...
0
votes
1answer
31 views

Regression/Optimization models that factor in the conviction of the predictive values

This comes up in a problem I meet in practice. Consider the classical regression of combining two predictions together to form a stronger prediction $Y \sim X_1 + X_2$. Here essentially we generate ...
1
vote
0answers
24 views

Bayesian Model Averaging (Bayesian Averaging of Classical Estimates) Issue

I am trying to implement a method used by this paper (Described briefly at the bottom of page 3): From what I understand, it does 2$^k$ OLS regressions each time step to forecast the next time step ...
4
votes
2answers
36 views

Combining non-probabilistic models for higher quality predictions

Three people have independently developed models for predicting a coin flip. They take into account the launch angle, launch force, rate of spin, and various other factors to produce predictive models ...
0
votes
0answers
8 views

Forecasts combination via weights based on normal distribution

I am working on combining forecasts. I thought of calculating the weights based on normal distribution. This latter is fitted on the past values of the time series. My issue is, should the weight be ...
0
votes
0answers
16 views

How to combine predictions of different transformations of an underlying random variable?

I am adding some extra more statistical context on the mathematical post here: https://math.stackexchange.com/posts/3798022/edit When dealing with general predictions, we live in high dimensions. In ...
0
votes
0answers
19 views

Combination of different estimates of the same quantities?

Suppose we have $n$ number of estimates for a parameter, each derived independently. How will one combine these estimates to get a single estimate which has lower variance than each individual ...
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
vote
0answers
69 views

How can I calculate Conditional expectation using copula

Let X, Y two time series and $F_{i, \beta_i}$ the marginal distribution of residual of each time series and beta is vector of their parameter. I studied the dependence between this two series using ...
0
votes
0answers
19 views

Part Univariate and part Multivariate Timeseries forecasting problem

I have a forecasting problem: Data from 1-1-2015 to 8-31-2019 is Univariate (Weekly) Data from 1-1-2017 to 8-31-2019 is Multivariate (Weekly) Final predictions need to be made from 9-1-2019 to 12-...
0
votes
0answers
6 views

Is Bregman Divergence useful in applications for combining (marginalized) probability densities of transformed variables?

I see a lot of theoretical results about the right way to think about solving for $P(y_0, y_1, ...)$ given information about "marginals" (i.e. transformed views of the underlying $y$) $P(f_i(y)), i=1,\...
2
votes
2answers
96 views

Lasso for Ensemble Learning, base learner selection

In ensemble learning, we average the predictions of multiple base learners (e.g. SVM + ANN + Linear regression). Instead of taking the mean of the individual base models' predictions, can lasso be ...
2
votes
1answer
143 views

Forecast combination using optimal weights

I am struggling with a case where I am supposed to calculate optimal forecast weights of two forecasts. We have fitted the models on a training set (time series) and want to calculate optimal weights ...
0
votes
0answers
23 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?
4
votes
1answer
114 views

Combination of correlations: How to correlate compositions?

How to correlate a set of compositions to a same-sized set of estimates of these compositions? -> composition(estimated) vs composition(real) Imagine you have a mixture of 5 liquids A+B+C+D+E, ...
0
votes
1answer
61 views

Averaging individual predictions in a group

I created linear model to give prediction for a team member (individual). Can I use this model to give average (individual) prediction in a team by providing average values of features among team ...
0
votes
0answers
18 views

Forecasting time point not value

I have a simple question. when we want to forecast a time series, we always focus on the value of series in future. But could we forecast time point of spesific value? For example I would like to ...
1
vote
0answers
88 views

Combining regression models from separate data sets

What is the best way to combine regression betas from separate data sets? For example, a data set is split in two based on some fundamental characteristic, and the same two factor regression is run ...
2
votes
2answers
444 views

Weighting of multiple linear regressions in an ensemble

If I have a continuous dependent variable and N continuous predictors, and I fit all possible regressions with zero up to N variables, how should I weight those regressions for prediction? One ...
1
vote
1answer
69 views

Combine mutliple predictions

This question had been asked several times in here, but I think I have something new to add. I'm interested in predicting if some specific event will happen (binary classification). I have two ...
1
vote
1answer
27 views

Combining forecasts or distributions to form a more accurate one

Suppose you are interested in getting as good an estimate as possible for a random variable $X$, this could be for example a stock price in the future. You go to see $N$ experts, each gives you a ...
2
votes
1answer
145 views

Combination of hierarchial time series forecasts with different methods - setting weights

I am trying to forecast the the number of orders for different products of a product group. I have the time series for each product. One of the problems is that some/most time series are intermittent ...
2
votes
0answers
43 views

What are the algorithms for fusing time series together [closed]

Assume I have multiple time series with the same length and the same range. What are the different algorithm used to fuse the time series together? what techniques would the best to combine them to ...
1
vote
1answer
2k views

time series forecasting in R for a period less than 2 years(18 months) which is totally random

I'm working on a project of forecasting. I have the count of the purchase order for an 18 months period of time. I'm attempting to create a forecast from time series data that has observations only on ...
1
vote
1answer
981 views

A Function to select a forecast method

I often have more than one time series to fit a model. Thanks to forecast and forecastHybrid packages they make easy to fit a ...
0
votes
1answer
123 views

How to weight several noisy estimates of the same value

If you have a variety of noisy estimates/measurements of a single value, what is the best way to combine them in order to estimate the underlying value? I have looked at "Unknown Constant in Additive ...
1
vote
0answers
675 views

Using information about covariance between ARIMA models in forecasting

I'm interested in how to incorporate information about the covariances of related timeseries from multiple univariate forecasts into each forecast. The ultimate goal of this is to implement ...
0
votes
2answers
89 views

Price change in forecast

I recently joined a online retail company and the way they have been doing forecasting and inventory management is not good at all and I'm working on improving the forecasting of the products. While ...
1
vote
1answer
323 views

Simulation based on BSTS model

Currently I'm fitting different time series models and produce combined n-step-ahead forecasts. As finding prediction intervals (analytically) for combined forecasts is quite a hassle, I decided to ...
1
vote
0answers
53 views

Combine and reconcile forecasts

I am struggling conceptually with how I can best model my panel dataset. I have a set of individual data and I need to: 1) estimate the median value of the dependent variable over time in the entire ...
1
vote
0answers
191 views

Finding relevant combinations of predictors

I am currently working on a data set consisting of 300 predictors and a dependent variable. The predictors are categorical variables (taking values 0,1) and for every observation only a subset of them ...
2
votes
1answer
778 views

Optimization of Mean Absolute Error with regularization

i have two different weather forecasting systems. Each system returns values between 0 and 30 degrees. In addition i have a grounded truth set containing the real temperature values. Now i want to ...
3
votes
1answer
137 views

Approaches to average forecast in machine learning?

I have researched some approaches so far. My situation is: I have 9 different models, all targeting on the same time-series variable. Now I want to combine these 9 forecasts to estimate a better, ...
3
votes
3answers
108 views

Arguments against model or forecast combination?

Do you know any references providing arguments against model or forecast (models output) combination? Could not find anything
3
votes
2answers
544 views

Do model averaging and model combination mean the same?

I am not sure, but I guess model averaging and model combination and even forecast averaging and forecast combination are used arbitrarily in the literature... Is this only my feeling or indeed the ...
0
votes
2answers
542 views

Time series forecasting with a combination of methods

So, i read this article: https://www.r-bloggers.com/timeseries-forecasting-using-extreme-gradient-boosting/?utm_source=feedburner&utm_medium=email&utm_campaign=Feed%3A+RBloggers+%28R+bloggers%...
10
votes
1answer
2k views

Model averaging approach — averaging coefficient estimates vs. model predictions?

I have a basic question regarding approaches to model averaging using IT criteria to weight models within a candidate set. Most sources that I have read on model averaging advocate averaging the ...
6
votes
1answer
1k views

Weights to combine different models

I have built different classification models (logistic regression, randomforest, and xgboost) for a dataset. I would like to combine the prediction of all the models to reduce the variance and ...
0
votes
1answer
914 views

Caret package - Is it possible to compute predictions for non-optimal models?

Not sure if this post belongs here or if stack overflow would be more appropriate. I am starting to familiarize with the caret package in R which seems very powerful for the purpose of optimizing and ...
3
votes
0answers
1k views

How to implement Bayesian Model Combination?

I'm interested in formal procedure mentioned in "Turning Bayesian Model Averaging Into Bayesian Model Combination" (Kristine Monteith 2011). I have a set of $N$ "best" AIC ranked models and I want to ...
2
votes
0answers
64 views

Combining Forecasts: Best Information to Solicit from Forecasters?

Suppose Statistician $m=1$ produces a set of $h$-step-ahead point forecasts $\hat{x}_{t+h|t, 1}$ of $x_{t+h}$ where $x_{t+h} \in [0,1]$. Also, this point forecast could come with: a predictive ...
2
votes
1answer
36 views

Dangers of averaging between model approaches

I am working with some ridership data that is broken down by route, year and month. I have built and tested a whole bunch of models ranging from GLM, GEE, GENLIM, and Panel and ARIMA data models. I ...
9
votes
2answers
3k views

Assigning Weights to An Averaged Forecast

So I've been learning how to forecast over this summer and I've been using Rob Hyndman's book Forecasting: principles and practice. I've been using R, but my questions aren't about code. For the ...
1
vote
2answers
1k views

How does Weka combine the decision trees in a random forest?

When building the random forest, I am wondering if Weka combine the decision trees by averaging their probabilistic prediction or if Weka let each decision tree vote for a unique class?
38
votes
7answers
16k views

Combining probabilities/information from different sources

Lets say I have three independent sources and each of them make predictions for the weather tomorrow. The first one says that the probability of rain tomorrow is 0, then the second one says that the ...
2
votes
2answers
1k views

More Statistical Way to Average N Predictions

I've run a RandomForestRegressor (Scikit Ensemble) over N loops, each time changing the random seed and therefore changing the train test split. This way I've N sets of predictions (M predictions for ...
2
votes
2answers
809 views

Model averaging in prediction — “Wisdom of the Crowd”

Suppose I'm trying to predict $Y$ (a real number) and I have $n$ experts with guesses $Y_1,...Y_n$. Each prediction is a reasonable guess as to the value of Y in itself (hence the name "expert"), but ...
6
votes
1answer
940 views

How to make a combination (aggregation) of quantile forecast?

Framework. Fix $\alpha\in ]0,1[$. Imagine you have $n$ $\alpha$-quantile forecast methodologies that give you, at time $t$ for look ahead time $t+h$, an estimation of the quantile of wind power. ...