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

2
votes
2answers
105 views

Difference between descriptive and predictive modelling

I was wondering if anyone could help me clear up the difference between descriptive and predictive modelling. I am trying to build a model to predict where house prices will go up. To do this I need ...
0
votes
2answers
53 views

What's wrong to fit periodic data with polynomials?

Suppose we have toy daily temperate data and we want to fit a model. A reasonable thing to do is fitting a periodic model with Fourier basis $$ f(x)=\beta_0+\beta_1 \cos(2\pi x/24)+\beta_2 \sin(2\...
1
vote
0answers
31 views

Importance interpretation with randomForest using R

I'm working on a predictive model using randomForest. I have some interesting results but the important variables got me confused. While using the varImPlot from ...
0
votes
0answers
9 views

How to fit a forecasting model on this irregular time series in Matlab to obtain predictions? [on hold]

We have some data values from the past (1214415 to be exact over 1 minute intervals). We are only interested in the 'peaks', that is, how the trend pertaining to the maximum is increasing with time. ...
0
votes
2answers
22 views

How to calculate probability of success based on prior p-value

The FDA often requires a sponsor to conduct multiple clinical trials prior to approval. Given the following observations in a ph2 and ph3 trial, how would you go about predicting the probability of ...
2
votes
1answer
17 views

Are there any models that can handle out of sample features?

So I'm facing a regression problem where I have a categorical features (factor) where the levels are very commonly different between the training set and the test set. I have multiple measurements ...
0
votes
0answers
5 views

What are some viable models for all factor variables?

I have a dataset where everything, including my target dependent variable(s) are factors. Maybe I'm lacking creativity on this one, but what are some viable, predictive, models for something like this?...
1
vote
1answer
33 views

Should OLS always have a lower RMSE than Poisson Regression?

I'm working on building a predictive model for the number of singles a hitter in baseball generates over the course of a single game. Since the number of singles a hitter scores per game is count data ...
0
votes
0answers
7 views

what should be validation parameter for Logistic Regression(LR) in online learning plus rare event scenario?

We have been following below paper to predict CTR( Click probability) of different ad items. This will be used to serve different ads based on probability values. http://olivier.chapelle.cc/pub/...
0
votes
0answers
57 views

Prediction Algorithms in Statistics

Here it is what I'm looking for: Having a random variable, with an unknown distribution of its values, is there any smart algorithm that can predict the next value of the variable based on n samples ...
0
votes
1answer
17 views

Can I use information about the distribution of the dependent to improve prediction?

I'm trying to make predictions about a quantity on a per-subject basis. If I aggregate my complete sample I can get very good fit for distributions like gamma or Weibull, so I can make some ...
1
vote
0answers
24 views

Optimal prediction strategy with unstable parameters

I got a, at least for me, unusual data set at hand which I employ to create a prediction model for fresh data streaming in. For specific reasons, I only got "one shot" to build the model: That will ...
1
vote
1answer
19 views

Using different prediction models/algorithms for different subsets of dataset

Is there practice in data mining and machine learning where different parts of dataset are predicted using different algorithms/models? The logic is that some data samples are better predicted with ...
0
votes
1answer
37 views

Request for reference of cheat-sheet of paper concerning preprocessing and learning algorithms [closed]

Is there a comprehensive list of preprocessing steps that are highly recommended when using the classical learning algorithms (see below for a list of the families)? Is there a cheat-sheet or a cook-...
0
votes
0answers
10 views

Is it accepted to fit model with standardized data and predict on non-standardized data? [duplicate]

If you standardize your training data, then can it work on unstandardized data during predictions accurately? Many algorithms require the feature data to be standardized and I am wondering how/why/...
0
votes
0answers
18 views

Stock Price Prediction using Forward or Viterbi?

I've run a simulation with my data (using the Hidden Markov Model) and obtained my transition matrix, my hidden states and parameters. I am now wondering which algorithm would be able to predict (and ...
0
votes
2answers
24 views

Getting information from a GBM model

I built a gbm model (using caret package) in order to predict the probability of someone buy or not a car. However as this kind of model act as a black box my issue is to replicate the "profile" of ...
1
vote
4answers
93 views

How to increase the accuracy of my logistic regression model?

I am dealing with a tricky, unbalanced data set and trying to run a logistic regression model. One class is present with a 10:1 ratio. My objective here is to boost my predictive accuracy - minimize ...
0
votes
1answer
18 views

Predicting continuous position using input variables of unknown quality

The problem I'd like to solve can be reformulated as follows. Let's consider that I have to go to some parties and I would like to find out where in the room I am most likely to have a good time. I ...
1
vote
3answers
29 views

How should new variables to be added in logistic regression model in production?

We have built a LR model ( online SGD ) in Spark. There are more that 15 categorical variables only as independent variables.At run time new values come in few of the columns. We have used ...
0
votes
0answers
28 views

How to build model given data only?

Given data only and without any (prior) knowledge or information about the data, how to construct a model for the data and predict new data? There are many statistical models but I have no idea which ...
0
votes
0answers
30 views

What statistical analysis for identifying sections of

I am a stats novice, and dont quite know the method to use in my problem. So I have a set of independent variables, and I want to find what sort of prediction strength exists with some dependants. ...
0
votes
1answer
20 views

Chossing an algorithm when there is only one feature

I am combining multiple base classifiers for an ensemble classifier. Different sensors, such as an accelerometer, gyroscope and altimeter are classified individually, and their outputs are then fed ...
1
vote
0answers
20 views

Ensembles - few questions on approach with multiple models

I'm looking for some general-high level understanding of how I should apply ensemble techniques. I understand that some models can be already thought of as ensembles - such as random forests or some ...
1
vote
0answers
52 views

Time series prediction in R over more than 180,000 past data points takes forever?

We have data values pertaining to BPS (bits per second) traffic on a networking device. We have data from for a particular month (October) from the past 4 years. The data points are available in a 1 ...
0
votes
0answers
11 views

Projection Pursuit Regression

I am trying to use Projection Pursuit Regression to fit a model to my data set, but I am running into some difficulties. I have a few questions: 1. Can PPR only be used when you have many predictors? ...
0
votes
0answers
9 views

Predicting End Year based on Beginning Year - weighting time-based feature values

I apologize if this has been answered in the past, but I have not been able to find anything relative to this type of scenario. Our goal is to predict when an owner of an asset will sell that ...
0
votes
0answers
4 views

Is it sensible to roll up the revenue predictions?

I have a general doubt on how to make predictions. for example: Scenario A: Predict revenue by (Year | Quarter) Scenario B: Predict revenue by (Year | ProductA | ProductB | ProductC | ProductD) ...
1
vote
1answer
30 views

Comparing performance of two k-fold cross-validated models

I'm developing two k-fold cross-validated models, based on two different data sets, but using the same variables. I plan to then apply both models to each data set and calculate a few model ...
0
votes
0answers
51 views

Time series prediction in R where data is available over past 4 years in 1 minute intervals

We have data from 'october' in the past 4 years and we want to predict what data for this year is going to look like in October. The data looks like this: 1 2 3 4 5 6 ... Every october has 31 days, ...
0
votes
0answers
3 views

Reading time series data into R when you don't have time labels? [migrated]

We have a data set that is in a very strange format. It mentions the start date and the end date and time and then goes into data values. See the format sample below: ...
0
votes
0answers
12 views

Incorporating demographic features to the BTYD model

Currently I am working in a project which requires Buy Til You Die model.It takes into account only the purchasing history of a customer.I want to know how can I incorporate demographic feature of a ...
7
votes
1answer
380 views

When have I to stop looking for a model?

I'm looking for a model between stockprices of energy and the weather. I have the price of the MWatt bought between the countries of Europe, and a lot of values on the weather (Grib files). Each hours ...
0
votes
0answers
22 views

How can I overcome the “contrasts can be applied only to factors with 2 or more levels” when each factor has 1 level?

I have trained a model and now I want to predict the output for a new query with an svm. First, I got this error "length of 'center' must equal the number of columns of 'x'" which means that there ...
0
votes
0answers
15 views

Why regression trees in gradient boosting?

In the Gradient Boosting method, regression trees are used to model the residuals. Why specifically regression trees and not other? Can we use other?
1
vote
0answers
15 views

Pandas Time Series DataFrame Missing Values

I have a dataset of Total Sales from 2008-2015. I have an entry for each day, and so I have a created a pandas DataFrame with a ...
0
votes
0answers
24 views

Single pass object detection

Let we have a set of images $\{\mathcal I_i\}_{i=1}^n$ with labels $\{\mathcal B_i\}_{i=1}^n$, where each $\mathcal B_i$ is a set of regions. The problem is to find a function that given image $\...
3
votes
4answers
352 views

Logistic Regression: Does my model selection process make sense?

This is kind of a broad question and so I am okay with broad or general answers. In fact, each of these could be their own individual questions, but I think it makes sense to ask them all. Even if you ...
0
votes
2answers
33 views

Assigning a transfer value of a Football player given performance scores

I just recently landed my dream internship at a football statistics company and I am eager to impress. I have an excel spreadsheet of every player in the major leagues along with the minutes they ...
1
vote
1answer
35 views

How confident can you be of prediction accuracy, even in the case of a causal relationship?

If we use the example of the correlation between frequency of cricket chirps and temperature, where there is a causal relationship between temperature and crickets' chirping rates; it seems to me we ...
1
vote
1answer
31 views

Is there a non-boostrap way to estimate confidence intervals for Kernel regression predictions?

Simple problem of estimating: $$ y = f(x) + \epsilon $$ Where I use your standard Nadaraya-Watson Regression to guess $f(x)$. This is relatively fast and works well even in an online setting. Now I ...
0
votes
0answers
10 views

Proving that lagging results is sufficient to prevent foreknowledge in model

I am trying to explain to a friend why lag prevents foreknowledge in a model. The example that sparked the discussion is here:quantstattrader My Attempts Shifting the prediction back by one wouldnt ...
0
votes
1answer
58 views

Predict results of Elections

I have information on the votes in my town and in the country. I want to predict the results in the country's elections knowing the results in my town. What methods I can use? I have thought of ...
0
votes
0answers
7 views

Prediction whose distribution is shifted and is more leptokurtic

I have a model that, based on subject matter knowledge, should give predictions which have about the same density distribution as the training data. The actual predictions have a similar shaped ...
0
votes
0answers
5 views

How does Quest differ from, for example, C&RT or C5.0?

SPSS Modeler has implementations of a number of decision tree data mining algorithms. Some of them are relatively well-known, such as C&RT and C5.0, some slightly less so, such as CHAID and QUEST. ...
0
votes
0answers
39 views

How to prove the reliability of a predictive model to executives?

I trained data from 500 devices to predict their performance. Then I applied my trained model to a test data set for another 500 devices and show pretty good prediction results. Now my executives want ...
0
votes
0answers
22 views

Torch - SparseLinear nn to handle large inputs and large output for a prediction problem

I'm pretty new to the magic of torch7 and seek your help/advice for a problem of mine. Context: I am working on a prediction problem. We observed a certain pattern in our values and would like to ...
1
vote
2answers
65 views

Suggestions for appropriate regression models? [closed]

The image is like a larger version of the one posted, but not as clear. I am trying to find a model that can fit to that pattern so that I can identify when there is a break in the pattern. I am ...
0
votes
0answers
13 views

Why are the estimated probabilities of event from a multivariate logistic regression model equivalent to the crude event rates?

I have a large dataset (19k) and I am using logistic regression to estimate probabilities of experiencing an event at the patient level. I am interested in looking at the effect of a facility ...
0
votes
0answers
22 views

Is Logistic Regression Appropriate for this Question?

I am attempting to predict the ranking of NBA teams next season based on the number of games they won this season. To do this, I thought I could use a logistic regression with historical data. As ...