Predictive models are statistical models whose primary purpose is to predict other observations of a system optimally, as opposed to models whose purpose is to test a particular hypothesis or explain a phenomenon mechanistically. As such, predictive models place less emphasis on interpretability and ...

learn more… | top users | synonyms

1
vote
0answers
7 views

R Caret - Repeated CrossValidation, finalModel and ROC curves

I got a problem understanding the meaning of the finalModel when using a repeated CV. ...
1
vote
0answers
7 views

Multiple time series - class of problem with agents and events?

I'm working on a prediction problem and struggling to find applicable resources (articles, tutorials, papers) that address this class of problem. I'm assuming the info is out there and I'd love to ...
0
votes
1answer
15 views

Predictive Analytics, Rare Outcome, Multiple Regresson [on hold]

I'm looking at a data set with ~50,000 observations, ~800 outcomes of interest, with ~30 dichotomous (yes/no) variables for each observation. My goal is to create a predictive rule that will predict ...
0
votes
0answers
16 views

Determining sample size of skewed data

I have seen questions asking about sampling with non normal data but did seem to help. I have two datasets, dataset A containing results of students before ...
1
vote
0answers
13 views

Should I use 'sample standard deviation' for 'prediction intervals' and 'standard error of the mean' for 'confidence intervals'?

I just want to make sure I am getting this right. When I am concerned about the "result" of any particular new datapoint I should use prediction intervals not confidence intervals. When I am concerned ...
1
vote
1answer
13 views

Should I perform parameter tuning on the balanced or imbalanced dataset?

Consider a binary classification problem. As far as I know, if the dataset is imbalanced and if the two classification errors are not equally serious, then we should balance the distribution of the ...
0
votes
1answer
22 views

Compute accuracy of model evaluation

Say the number of negativ classes is $9990$ and the number of positive classes is $10$. If a model predicts all examples to belong to the negative class, how accurate is this prediction? So what we ...
2
votes
0answers
9 views

How to interpret the fitted functions in a GAM?

I don't understand how much I can trust in the fitted functions estimated in a generalized additive model. Look for instance to the plot b. The estimated function appears to be increasing but the ...
1
vote
0answers
21 views

time-series analysis / forecast compared to real planning (controlling) departments?

The following case study: Planning and forecasting in a volatile setting by Amy Wheeler, Nina Weitkamp, Patrick Berlekamp, Johannes Brauer, Andreas Faatz and Hans-Ulrich Holst, published in Rob ...
0
votes
0answers
5 views

What good is the lift metrics in a churn prediction model?

I am having trouble understanding how is the lift metric useful for my churn prediction model. I read this post, which was kind of clear for the example given, but can't completely link it to my case: ...
3
votes
1answer
49 views

How to find “theoretically best” model?

Given the common problem of predicting response variable $Y$ from predictor variables $X$ and $Z$, is there any way to determine the "theoretical best" prediction possible for a response variable? ...
0
votes
1answer
60 views

logistic regression predictive modeling

I would like to use a logistic regression for estimating the parameters of the logit function by using the maximum likelihood estimate. This amounts to minimizing the log-loss function, instead of ...
1
vote
1answer
35 views

Test/Measure for Rank Ordering a Logistic Regression model, invariant to event rate and population size

I have a model whose purpose is to rank order event risk - the output of which is split into twentiles (which have been based off the benchmark data). Currently, I'm using Somers' D calculated on ...
0
votes
0answers
10 views

Data setup: Attrition/Churn Modeling with Time Dependencies

Beginner Data Scientist here... I'm setting out to build a predictive model for our client in the hotel/hospitality industry to explain the factors contributing to the attrition of their Loyalty ...
0
votes
0answers
6 views

Identifying weak points in a predictive model

I have three variables $A$, $B$ and $C$ which affect a dependent variable $Y$. The variable $A$ is a measure of income inequality which can be quantified in many different ways (standard deviation ...
0
votes
1answer
62 views

Time series analysis for predicting a binary outcome

I'm fairly new to time series analysis. I want to analyze two series of variables in a span of time to predict a binary outcome. For example i collect data over time at my home of two variables: ...
0
votes
0answers
28 views

Sampling rate and regression

I am interested in developing a regression model. The data (about 1000 observations) that I have are not really random (i.e., spatially, the closest ones are correlated to some degree), so I drew a ...
1
vote
2answers
61 views

Weighting time series data for prediction

I am building a simple random forest to predict soccer results in sckit. I simply train the model to predict each teams score based on various features. However I am trying to think how I can weight ...
0
votes
0answers
22 views

How to compare the feature importances produced by two different classifiers?

In one study, I am using two different classifiers. I want to compare the feature importances produced by two classifiers. Is there a statistical technique to measure the similarity between the two ...
0
votes
0answers
23 views

Inferences from PCA plot

I have done a dimensionality reduction of binary labelled data (0,1 labels) from 300 features to 2 features. The plot looks like - What kind of inferences can I make from this plot? Can I infer - ...
0
votes
0answers
21 views

R H2O Telco Churn Prediction Expected Error Rates (Precision and Recall)

I have a simple question, I'll try to formulate it as simple as I can. I am modeling a churn predictor for a telco company. I am using H2O with R, and have run some tests. My data set is the whole ...
0
votes
0answers
16 views

Framework/tool for scalable automatic model training in batch and online?

For a retail problem, we need to build model for every individual customer on their accumulated historical data on a periodical basis. This is to predict certain classes individually. For a ...
1
vote
1answer
15 views

Combine multiple predictions of binary outcome

I am moving from a single-model prediction of a binary outcome to an aggregate of a small number of models, for example: ...
1
vote
0answers
24 views

Using an RNN/LSTM to generate sequences with a unique output

I'm trying to train a LSTM recurrent neural network where my data consists of a sequence of animal migration data ...
0
votes
1answer
31 views

p-values of the coefficients or AIC for model selection in multiple regression

I´ve got two models from a multiple linear regression (A and B, see below) and don´t know which to select. I want to predict a value called AW as good as possible, so I´d like to have the highest r². ...
1
vote
0answers
15 views

Converting nomogram to logistic regression coefficients and intercept

My plan is to use a published nomogram to predict events in my data set. The question is, how do I derive logistic coefficients and intercept from the nomogram?
0
votes
0answers
10 views

Choice of the objective function in linear model

I'm reading the book "Data Analysis and Data Mining" by Adelchi Azzalini and Bruno Scarpa. At the end of chapter 4, the authors consider a regression problem in which the response variable is always ...
0
votes
0answers
13 views

Predict pairwise identity matches between elements

I want to build a model to predict identity matches between elements. My data is as follows: the predictors (X) are some bag of words representation or other ...
0
votes
0answers
6 views

How to extrapolate when feature scaling

Feature scaling refers to a transformation of a variable $x$ so that it lies in range $[0, 1]$: $x' = \frac{x - \text{min}(x)}{\text{max}(x)-\text{min}(x)}$, and it depends on the maximum and ...
0
votes
1answer
20 views

Prediction without labelled data

I am working on a churn prediction model, where I am trying to predict probability of employee churn. For each employee I have the following features 1) Role 2) Total experience 3) Current experience ...
0
votes
1answer
15 views

Trying to get predicted values from the estimate linear regression model but getting error message regarding dichotomous variable

please see my data below. Math: Centered math score (used for assigning students to treatment/control group) Assignment: whether the subjects are assigned to treatment group or control group (1 = ...
0
votes
0answers
21 views

What techniques I should look to predict next user behavior in a series?

I have a dataset, when users repeat an action (let's say, to choose a value between 1 and 10) many times (let's say 10 times). I want to predict the behavior of users at the 10th action, based on his ...
0
votes
0answers
18 views

Predict count data for unsurveyed areas

I am looking to predict count data from deer surveys for the unsurveyed areas. I want to make these predictions based on vegetation type and size of the vegetation type (acres). I started by using ...
0
votes
1answer
48 views

Which model should I use to predict pass/fail scenario?

I am new to predictive modelling. I am unable to choose the correct model for predicting if a student will pass or fail a particular exam. My data set : Input variables: Total_tests_Taken , ...
0
votes
1answer
33 views

Is it correct to perform parameter tuning after nested cross validation?

Suppose that we have 3 different regression/classification methods: $f_1(D,\alpha)$, $f_2(D,\alpha)$, $f_3(D,\alpha)$ (for instance: lasso, neural network and SVM) where $D$ is the dataset and ...
0
votes
1answer
29 views

How to handle missing data for prediction with small data set

I have to analyse the results of american football players. The goal is to predict the position group based on the results of about 20 exercises. Therefore I use SVM, Neural Network, Decision Tree, ...
1
vote
2answers
43 views

Multiple regression with highly correlated variables

I have to do a multiple regression in order to predict the GDP, using some (or all) of the variables that I have (consumption, investment, govt expenditures, disposable income, price index, money ...
1
vote
1answer
37 views

How is the standard error of the estimated prediction error calculated?

I'm reading the book "The Elements of Statistical Learning" (Hastie, Tibshirani, and Friedman). At page 62, they present the estimated prediction curves with the standard errors for best subset ...
3
votes
1answer
61 views

Decision Trees and Regression - Can predicted values be outside range of training data?

When it comes to decision trees, can the predicted value lay outside of the range of the training data? For example, if the training data set range of the target variable is 0-100, when I generate my ...
0
votes
0answers
14 views

want to evaluate the performance of my model

I have developed a machine learning model to predict outcome of cricket matches and the accuracy I am getting from my model on the test set is 65% and on the training set is 66%. I want to know if it ...
3
votes
0answers
25 views

Linear model with biased estimator

Consider a linear regression model. Suppose that the estimator $\hat{\beta}$ for the vector of the parameters of the model $\beta$ is, for some reasons, biased. As a consequence: ...
0
votes
1answer
33 views

Does multicollinearity affect performance of a classifier?

I know that wikipedia references are sometimes frowned upon here, but this one has me puzzled: Wikipedia - Multicollinearity I know what multicollinearity is, and ...
1
vote
1answer
51 views

Accuracy of training sample in Random Forest model in R

I'm using a Random Forest algorithm in order to construct a classification model, and I HAVE to check the accuracy of my rf model in the training sample, but as you can see in this answers : ...
0
votes
0answers
20 views

Predict individual data from aggregated data

I'm trying to construct a model in order to establish a relation between the non performing loans of an specific bank and the non performing loans of the entire system. Since the data of the latter ...
5
votes
3answers
159 views

How to check for the distribution stability?

I need for verifying that the training set I'm using to build a model is equally distributed to the test set. The model is for prediction purposes and I think it is necessary the 2 samples are ...
0
votes
0answers
6 views

how to use a comparison between two ordinals as a regression predictor

I'd like to predict which species is likely to dominate the other in a pairwise interaction between species. In the literature on dominance hierarchies ("pecking order"), what's usually considered to ...
0
votes
0answers
24 views

emission matrix in hidden markov model

I'm using a Hidden Markov Model for fraud prediction in credit card. I have already created the transition matrix using data from a set of training data data in term like this LLMHLHLMMLHH. I can't ...
4
votes
1answer
47 views

Pseudo-random sequence prediction

Disclaimer: I posted this question on CS about a month ago, but haven't gotten any response, despite positive rating. It has been suggested that I repost the question on CV, so here goes. Imagine ...
0
votes
0answers
23 views

Different Loss Functions used when fitting the model and tuning hyperparameters with cross validation

I usually do a two step process to fit a model: Given a hyper-parameter, fit the model using some criterion, such as MLE, etc. Do a k-fold cross validation and try a different hyper-parameter on ...
0
votes
0answers
12 views

How to shift a set of predicted probabilities to achieve an overall expected class distribution

I have a model that predicts a set of k class probabilities for each of n samples. Something like ...