Questions tagged [classification]

Statistical classification is the problem of identifying the sub-population to which new observations belong, where the identity of the sub-population is unknown, on the basis of a training set of data containing observations whose sub-population is known. Therefore these classifications will show a variable behavior which can be studied by statistics.

2,022 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
2
votes
0answers
143 views

How to compute gain statistic for the multinomial Naive Bayes classifier from Jurafsky and Martin (2018)

I'm trying to figure out how to compute the gain statistic G(w) following the fitting of the multinomial Naive Bayes model. This statistic is described on p17 of the new edition of Jurafsky and ...
2
votes
0answers
79 views

What is the number of filter when using CNN for sentence classification

I am new to machine learning and NLP. During reading convolutional neural networks for sentence classification I'm having trouble understanding it. In the paper it says that a feature map c has ...
2
votes
0answers
59 views

Combining multiple observation weights for classification

Let's say you have multiple sources of observation weights for a dataset. For example, you have a $[0,1]$ weight coming from the label's certainty ($w_c$) and another one coming from its recency ($w_t$...
2
votes
0answers
97 views

Probability score for Hierarchical classification models

We've a hierarchical classification system in place; where each level produces predictions with a probability. Here's how the hierarchy is setup Top level: 1 model; ~25 classes Level 1: 25 models(=25 ...
2
votes
0answers
160 views

Skewness Impact on Classification

I have a dataset with 134 attributes and my goal is to build a binary classification model. While exploring the dataset, I found that there was high skewness present in the attributes. I wanted to ...
2
votes
0answers
289 views

Interpreting units for random forest variable importance

I've trained a random forest for classification in R's caret package using the ranger method and impurity for measuring variable ...
2
votes
0answers
51 views

Calibrating probabilities of a binary classifier when class prior is unknown

Is it possible to calibrate the probabilities of a binary classifier when the class priors are unknown? In cases where the data is obtained with selection bias (i.e. more positives than negatives in ...
2
votes
0answers
110 views

Are latent variable models the same as latent source models?

I am interested in the research done in this thesis and accompanying paper. This research discusses models termed latent source models. I have never heard of this specific term and the papers don't ...
2
votes
0answers
489 views

Clustering as a method to find and label classes for supervised learning

I'm working on a text classification project. We have around 300k documents (small, 1~2 phrases) and we don't know the set of labels or how many labels there are. The recommended approach to me was ...
2
votes
0answers
29 views

SVM classifier: strange location of support vector

I am playing around with Matlab's example which involves classifying whether data lie inside a circle of radius 1 (label: -1) or out of it (label: 1). I decided to experiment with things and flipped ...
2
votes
0answers
63 views

What is an appropriate Evaluation Metric and corresponding Loss function which best optimize the metric for a classification based FAQ Chatbot?

I am developing a FAQ chatbot to display/return only one correct answer in a chat window for a given question from the user. I know MRR & MAP make sense as an evaluation metric for information ...
2
votes
2answers
221 views

improving classification accuracy of the dataset as a whole by considering classifier distributions

Overview I'm new to machine learning so apologies if I misuse terms. I have an idea to improve my classification analysis that I feel is not terribly unique, but I can not find a reference to such a ...
2
votes
0answers
39 views

Boosted decision trees: in which situations are “deep” decision trees performing better?

The general idea of boosted decision trees is to use very simple trees in the following manner (simplified, for intuition only): start with a simple tree, fit another simple tree on the residuals, ...
2
votes
0answers
153 views

Optimism bootstrap with non-linear models

I have come across an example in my research with heavily overfit non-linear probabilistic classifiers, where the optimism bootstrap appears to underestimate the optimism, even when using a proper ...
2
votes
0answers
203 views

VC dimension of rectangles in 2D space

I understand that the VC dimension of axis-aligned rectangles is 4 because there exists a set of 4 points that can be shattered by a rectangle and any set of 5 points cannot be shattered by a ...
2
votes
0answers
44 views

Unbalanced data on fire for a binary classifier

I have a lot of training data from which I want to build a binary classifier, but the classes are highly unbalanced, 97% in one class, 3% in the other (even though, in absolute terms, I still have a ...
2
votes
0answers
49 views

SVM optimization problem with constraint

I am studying SVM from Andrew ng machine learning notes. I don't fully understand the optimization problem for svm that is stated in the notes. So we have optimization problem $$\max_{\gamma, w, b}\...
2
votes
1answer
857 views

How to manually balance unbalanced multi-class/multi-label data?

I have a multi-class and multi-label classification problem, i.e.: each sample can have more than one label associated to it and there is a total number of M ...
2
votes
1answer
26 views

Classifying compositional vectors of time series

I am interested in classifying vectors of time series $x_t=(x_{1,t},\ldots,x_{n,t})$. In addition these vectors are subject to the restrictions $\forall i,t$: $0 \leq x_{i,t} \leq 1$ and $\forall t$: $...
2
votes
1answer
266 views

classification on imbalanced dataset via random forest: results vary with random seed

I have a highly imbalanced dataset of about 8000 observations, with 11 features and one binary target variable. I want to predict the target labels, considering that the "1" target label occurs for 1....
2
votes
2answers
198 views

How to choose a method for binary classifier based on only positive and unlabelled examples?

I need to build a binary classifier with machine learning, as I fail to manually choose a combination of features to achieve minimal fraction of false positives. What is best practice for choosing a ...
2
votes
1answer
500 views

Analogue of critical difference (CD) diagram for the comparison over single dataset

does anybody know any fancy way to present the performance of multiple classifiers (in terms of AUC, for example) over just 1, single dataset? I am familiar with the critical difference diagram for ...
2
votes
0answers
218 views

Similarity between Train and Test data sets

I have multiclass classification dataset and I am using Deep nets for the classification task. To explain the problem, let's assume that I have 5 classes to classify. No matter what I try, be it ...
2
votes
0answers
124 views

What is the definition of margin for multi-class classification?

I heard the definition was as follows: Let $y_{best} = arg \max_{c \in Classes} f(x)_c$ be the best class and let the prediction function be an output vector $f(x) \in R^{|Classes|}$. Then define: $$...
2
votes
1answer
804 views

Improve the precision of random forest for count data

I am trying to create a classification model that predicts whether a customer will enquire for a financial product based on some 250 independent variables. 98% of the variables are count variables and ...
2
votes
0answers
34 views

Classification models: finding name for specific loss function

Below is the linear classifier analogy, where the two lines are the decision boundaries with different thresholds that gives 0 false positive and 0 false negative respectively. A, B, C are sets of ...
2
votes
0answers
63 views

Classification method for biased training data

I am trying to use patent texts to make a binary classification of a large number of patents as either 1. related to automation or 2. not related to automation. I have manually classified a small non-...
2
votes
1answer
15 views

Classification problem: custom minimization metric to shift the focus of the model?

Assume a binary classification problem, with $1$ denoted as a "bad" outcome, and $0$ as a "good" outcome. If it's relevant, in the sample there are significantly more bads than goods, and this is the ...
2
votes
1answer
285 views

Difference between cumulative gains chart and cumulative accuracy profile for binary classifier

I am confused about the following: Here I find the definition of cumulative gains chart as the plot of x-axis: the rate of predicted positive y-axis: true positive rate It turns out that we can e....
2
votes
0answers
30 views

How does the expected risk change as we scale a classifier?

I wanted to understand what in the expected risk $R(f) = \mathbb E_{x,y \sim p(x,y) } [ \mathbb 1\{ f_W(x) \neq y \} ]$ when we scaled a classifier. To my understanding if we scale a classifier not ...
2
votes
0answers
22 views

How to build an automated classifier selection procedure?

I am working on a time series data based on remote sensing. I have applied different classification methods on data like RF, SVM, KNN, Gradient Boosting, etc. So, I have got different models and I ...
2
votes
1answer
34 views

Can an ML model choose between an arbitrary set of classes?

I want to build a model that can take in X sets of information (e.g. you can think of it like X python dictionaries, all with the same fields) and choose one out of the X based on a bunch of examples ...
2
votes
1answer
88 views

What kinds of algorithms work well with hundreds of thousands of output classes?

I have a limited amount of data for each class (about 100 samples), but I have about 100000 such classes. What kind of classification algorithm would work on this? (Apart from a NN with hierarchical ...
2
votes
0answers
525 views

Accuracy and F1 score for binary classification

Consider a binary classification, where the precision is 1 for one class and the recall is 1 for the other class. Thus, all false classifications are some elements of class 1 being detected as class 2....
2
votes
0answers
308 views

Classification: how important is the sample-to-feature ratio?

Some people mention you should have at least 5 times as many samples as features for classification problems 1. I've also heard people on here saying the sample-to-feature ratio is arbitrary and ...
2
votes
0answers
68 views

Decision tree ,information gain and overfitting

If i use the information gain in order to evaluate the best split in a decision tree, why using a binomial split reduces the risk of overfitting ? Is the information gain test misleading if we have a ...
2
votes
0answers
33 views

How to improve Naive Bayes?

I am solving a problem that address this question "What are the Actions that lead to high or low score?" I have the following Data that consist of text and score , I want to derive the words or ...
2
votes
0answers
114 views

How to calculate the prediction score of a classificator?

I want to compare a given classification algorithm with others via the Area under the (ROC-)curve metric. Unfortunately this algorithm only outputs the values of the respective confusion matrix (TP, ...
2
votes
0answers
149 views

Classification on multivariate time series

My dataset: 121 individuals characterized by a categorical variable let’s say Y (so 121 values of Y {low, medium, high}) for each individual, I have 5 time series, let’s say $X_1$, $X_2$, $X_3$, $X_4$...
2
votes
0answers
185 views

Binary Classification: good at predicting negative class but bad at predicting positive class

I used many different algorithms on a data set for binary classification. I used kNN, SVM radial, ANN, random forest, Gaussian process classification, etc. Every algorithm is well tuned in R using ...
2
votes
0answers
17 views

Fuzzy Aggregation

Each observation in the data consists of a binary outcome variable $Y$, a set of labelled measurements $(M_1,L_1), (M_2,L_2)...$ (the set size can vary between observations) where each label is one of ...
2
votes
0answers
47 views

Can/when should a trained classifier with summary statistics stand-in for a traditional hypothesis test?

In a project I'm working on, we'd like to show that certain stereotyped anatomical areas (represented by shapes at certain locations) are reproducible enough in terms of shape and location to be "...
2
votes
1answer
137 views

Higher Test Scores but Higher Variance?

I am tuning hyper-parameters using 5-fold cross-validated grid search for various multiclass classifiers, and I keep running into the same issue that I can't quite wrap my head around. The hyper-...
2
votes
0answers
405 views

How to choose threshold in probabilistic multi-label classification?

My problem is to tag some texts with some labels. That is multi-label classification in ML. I did predict with Catboost classifier and get some results of binary ...
2
votes
0answers
518 views

Resolving prediction ties for multi-class problems

Consider a multi-class problem with $c > 2$ classes. With this situation, the researcher is bound to deal with complication where there are prediction ties between classes. In my case, I've a ...
2
votes
0answers
1k views

Predicted probabilities for binary labels by Randon Forest and XGBoost

Task Binary classification for an imbalanced dataset with 70 positive samples and 700 negative samples Data Oversample positive samples to match the number of negatives. Each sample has 10 features....
2
votes
0answers
42 views

Determining important features from large number of features

From a large number of time series, I've generated an even larger number of features for each one. The result is a NxM matrix for times series N and feature M. Using Matlab, I could feed this dataset ...
2
votes
0answers
259 views

neural netork loss function for hierarchical classification

I am trying to use a convolution neural network to classify organisms into the correct phylum. It's easy enough to just treat this as a classification problem and train on some images of animals (...
2
votes
0answers
97 views

Data leakage concern in a binary classification problem

I have a binary classification problem (where 1 = broken and 0 = not broken) for machine engines under study. There are 25 continuous features over which I use to make predictions of 1 or 0 using ...
2
votes
1answer
1k views

Logistic Regression with gradient decent: Proper implementation

So after going through some machine learning courses, I tried to implement my own logistic regression, just to get a feel of it. My code: ...

1
3 4
5
6 7
41