Questions tagged [unbalanced-classes]

Data organized into discrete categories or *classes* may present problems for certain analyses if the number of observations ($n$) belonging to each class is not constant across classes. Classes with unequal $n$ are *unbalanced*.

Filter by
Sorted by
Tagged with
2
votes
1answer
1k views

Which performance metrics for highly imbalanced multiclass dataset?

I have a dataset with 5 classes. About 98% of the dataset belong to class 5. Classes 1-4 share equally about 2% of the dataset. However, it is highly important, that classes 1-4 are correctly ...
1
vote
0answers
21 views

Selecting training images for object verification(siamese network), different number of examples per object

I'm trying to build a model for object verification (my first not tutorial-guided project of this kind). I saw an approach using a siamese network in the coursera deep learning course by Andrew Ng. ...
2
votes
0answers
67 views

Is better to use a multiclass classifier or a set of binary classifiers?

I have to build a general method to perform multiclass classification. The number of class in the target variable is not fixed (it is probably in a range between 3 and 10). I would like to know if it ...
2
votes
1answer
765 views

geometric mean for binary classification doesn't use sensitivity of each class

scikit-learn's contrib package, imbalanced-learn, has a function, geometric_mean_score(), ...
0
votes
0answers
24 views

Sci-kit Learn Beta Score interpretation: How to use the 'beta' and 'average' param correctly?

I am building a model for a class imbalance problem, which I want to be as recall oriented as possible for the minority class. The model I have built uses class weights to penalize the majority class (...
0
votes
1answer
223 views

Imbalanced data for multiclass classification with ConvNet

I am trying to apply the SMOTE sampling technique to over-sample the minority class of a multiclass (5-class) problem using the convolutional neural network. As far CNN requirement, the input shape ...
1
vote
1answer
41 views

When working with unbalanced data, do we train final model on full data set?

Let's say we have an unbalanced data set. We randomly sample an amount from our larger class so that we have a balanced data set. After tuning parameters/hyperparameters and determining which ...
0
votes
0answers
26 views

Real life class imbalance [duplicate]

Fellow like-minded people, I'm writing my thesis in fake news detection on scrapped twitter data and facing an issue (among many others). Fake news consist of less than 10% of the total tweets or ...
1
vote
1answer
252 views

How R randomforest sampsize works?

I am working on a predictive model (imbalanced data) and trying to undersample the majority class data. I wanted to get the representative sample of my majority class and somehow came to know about R'...
0
votes
1answer
99 views

Should I upsample both my training as my test set?

I have a highly unbalanced dataset (1000 vs 60). Where I want to use upsampling. The real life distribution of the problem (predicting no show) is probably also very highly imbalanced. My question is ...
1
vote
1answer
61 views

What are benchmarks for precision when working with unbalanced data?

I have a dataset where the positive class is 1.7%, which equates to about 40k positive cases and a total basis of approx 2.5m. What is a realistic precision to achieve for the most likely to cancel? ...
1
vote
0answers
37 views

What is the affect of datasets having (Events Per Variable) EPV less than 10?

I read some studies in Software defect predictions (published in good journals) that mentioned that we should use datasets with an Events Per Variable (EPV) greater than 10; otherwise the results will ...
1
vote
0answers
17 views

Does My Custom Class Imbalance Handling Make Sense?

So I have a data set of size 250k, and my minority class is of size 5000. This is a pretty imbalanced dataset. I did not apply sampling in my model, and it turns out when split it into train, test, ...
1
vote
1answer
201 views

How to modify Presicion and recall of GLM (Logit) in R? [closed]

I fit a logistic regression model with an unbalanced population in R. The problem that I am getting is I have 0.4 for precision and 0.0018 for recall, so I want to modify the threshold in order to ...
1
vote
0answers
256 views

Improve F1-score for multiclass text classification with highly imbalanced dataset

I am trying to classify clients' complaints with a dataset of 180k complaints. I have 132 classes like this: Counter({'DIAG_000_NODIAG': 66291, 'FORWARD': 29126, 'DIAG_087': 22843, 'DIAG_049': 17668, ...
2
votes
1answer
97 views

Are mixed model results valid when several missing replicates?

I want to know if it is correct to take as valid the results of a mixed model (lme) test for a triple factor experiment with several missing replicates in only one level factor situation. My ...
3
votes
2answers
1k views

Why decision tree handle unbalanced data well?

one approach to deal with the unbalanced dataset is to choose the models that can hand this type of dataset well such as decision tree, but why decision tree can handle the unbalanced dataset well?
1
vote
1answer
31 views

Performance metric for continuous binary classification method

I have and imbalanced data set with two classes of data: $A$ and $B$. I apply a method that assigns a continuous probability to each element of belonging to class $A$: $P_{A}$ , where $P_B=1-P_A$. I ...
0
votes
0answers
63 views

Improving accuracy of multi-class text classifier

I am trying to build a text classifier with 4 highly imbalanced classes. Data has around 4000 documents and highly sparse. I have used XGboost and few other algorithms.Highest accuracy is given by ...
2
votes
0answers
293 views

Binary Classification Propensity Scoring: High Accuracy in Train/Validation/Test, but Low Accuracy on Production Data

Before I describe my problem, if anyone has material for propensity scoring I would love it if you posted some. I've done a lot of research on propensity, but I think I've bled myself dry on the net. ...
1
vote
1answer
98 views

Imbalanced dataset - Majority positive class

My dataset consists of 150 patients where 50 are controls/healthy (negative) and 100 are sick (positive). If I want my model to have high sensitivity at high specificity (left side of the ROC), in ...
1
vote
2answers
765 views

How to approach unbalanced data with unequal sample sizes for comparing means

I have a data with a continuous and two categorical (population and sex) variables. I want to test whether the means among the groups are significantly different. However, this is not an experimental ...
2
votes
1answer
245 views

Base rate of accuracy after resampling for classification problems

If I had an imbalanced dataset with 10% positive instances and 90% negative ones, the base rate for accuracy before resampling is 90%. But what about I resampled the data such that I have an equal ...
1
vote
0answers
47 views

Scaling baseline and SHAPs back to original class rate

I have an imbalanced dataset (positive class rate = 1%) and have downsampled the negative class to give me a 50/50 balance in the two classes. The outputs from this model look adequate. Ignoring the ...
0
votes
1answer
120 views

Classification models:Overfitting due to sampling issue

New to ML,I have used smote/sampsize for the first time, so sorry if the questions are very basic.I have a dataset with a factor response variable ("Y" , "N" )in the ratio(Y:N=3:7)(classification with ...
2
votes
0answers
19 views

imbalanced regression problem + lower bound prediction + custom error weighting

I'm looking for a simple approach (e.g. defining a new target label / sample weights and then using some off-the-shelf regressor with some standard objective) for the following problem: I want to ...
2
votes
3answers
216 views

Random undersampling: is there a way to chose the best majority samples?

I'm modeling credit fraud, where I have a small number of samples that result in fraud (1), and most samples that are not fraud (0). I am creating a models for detecting fraud based on new data. I'm ...
3
votes
4answers
2k views

classification imbalance data - bias and class weight

This page shows a classification problem. They have used bias as well as bias along with class weights. What is the difference between bias and weights? In some other techniques such as Random ...
1
vote
1answer
51 views

Problem of unbalanced data [duplicate]

unbalanced data is an issue that can effect the performnce of classification model ,several remides can be done to balance the data two of them are upsampling and downsampling , my questions is : how ...
1
vote
0answers
52 views

Will oversampling help with generalization (small imbalanced dataset)?

I have an imbalanced dataset (2:1 ratio) with about 60 patients and 80 features. I performed RFE + stratified cross validation to reduce the features to 15 and I get an AUC of 0.9 with Logistic ...
1
vote
1answer
51 views

How to improve Recall and Precision?

I am working on a big data set which has 25 features with 237862 number of rows. I am trying to predict return . 1 is for return and 0 for no return. My data set has 12% of data which returned. So ...
0
votes
0answers
26 views

Gains on test data set higher than that on training data set post balancing

I have an imbalanced data set (96-4 split between No and Yes cases). I am trying to build a decision tree model for classification after balancing my data set(tried different thresholds for ...
1
vote
0answers
239 views

How to perform Repeated Measures MANOVA, with unbalanced design [closed]

I am analysing data from a vaccination study and I think that the best way to model my data is with a repeated measures multivariate ANOVA. Because I have different #'s of subjects in each study ...
1
vote
1answer
21 views

How to handle a feature (x1) with huge sample space for linear regression ? (n(x1) >> n(x2,x3,…))

I have a regression problem to solve, comprising of approx 2000 data points. I have some 7-8 features, but one of the feature has a huge sample space, meaning When I one hot encode this Feature, it ...
1
vote
0answers
10 views

Regression/anova with imbalanced controls

I am thinking of a regression setup where the dependent variable, Y, is continuous and the predictor is a factor. The data is an aggregation of multiple sources with similar and pooled controls but ...
0
votes
0answers
2k views

Interpreting results of resemblance-based permutation methods: PERMANOVA and PERMDISP?

I am working with an invertebrate data set (i.e., counts of individuals per invertebrate order, captured by pitfall trap) and am exploring trends in community composition in relation to environmental ...
1
vote
1answer
3k views

imbalanced dataset - class weight vs weighted loss function

I'm working on a classification problem with a very imbalanced dataset. Many papers mention a "weighted cross-entropy loss function" or "focal loss with balancing weights". I can't find any of those ...
0
votes
0answers
24 views

Deal with imbalanced data [duplicate]

Building machine learning models to do forecast, sometimes the dataset was used is imbalanced, and there are some methods to deal with this issue such as the resample method and choose other metrics(...
0
votes
1answer
155 views

Binary Classification problem for imbalanced dataset

I am new to machine learning and need help. I have a dataset with two classes(0,1) where is 0 is Profitable and 1 is Unprofitable. Ratio of 0:1 in train set is 150/52 Taking positive as "1"(...
3
votes
1answer
373 views

Running SMOTE on very large class imbalanced datasets - batched or subsampled implementations

There is a theoretical and computational aspect to this question. I was trying to use SMOTE to reduce class imbalance in a rather large dataset--about 8 million rows. The data has a binary outcome ...
3
votes
2answers
640 views

Unbalanced data with logistic regression: good references?

I am using the logistic regression framework to formulate a classification model. I have a dataset with 42 'true' (response variable) values and 4400 'false' ones. By using the ‘rule-of-10’ and other ...
2
votes
2answers
246 views

Class imbalance, Random Over/Undersampling and the use of Class Weights and bias

I was looking at the Tensorflow tutorial on "Classification on Imbalanced Data". Now they first show how to apply some approaches to deal with imbalance using model weights and a pre-initialized bias ...
0
votes
0answers
115 views

Oversampling/Undersampling in respect to Train and Test - Isolation Forest

I've got a quite imbalanced data set. 144.496 : 162 -> ratio of 1000:1 I would like to use IsolationForest to detect the 162 anomalys. I've already split the data. However, the iForest doesn't ...
2
votes
0answers
15 views

penalized logistic regression for un-balanced classes--why does it make sense to keep all the zeroes?

So I have been looking at some public datasets on fraud detection, where the dataset contains a 0/1 column for whether the transaction is fraudulent and then a large set of numerical and categorical ...
2
votes
3answers
27k views

Chi-square Test with High Sample Size and Unbalanced Data

I have a data set which has high values. I want to make a chi-square test on this set. +--------+---------+---------+---------+---------+ +----------+ | 15-19 | 20-24 | 25-29 ...
2
votes
1answer
344 views

Why does a class weight fraction improve precision compared to undersampling approach where precision drops?

I have an imbalanced data where the ratio between positive to negative samples is 1:3 (positive samples are 3 times higher than negative). For my case it is is important to have a higher precision (...
0
votes
1answer
26 views

logic behind balancing? [duplicate]

I am a newbie in stats, and while reading: https://towardsdatascience.com/having-an-imbalanced-dataset-here-is-how-you-can-solve-it-1640568947eb I don't seem to understand why is an imbalanced ...
0
votes
0answers
38 views

Imbalanced data classification with GLM giving very poor results [duplicate]

I have a loan defaulters dataset and it is highly imbalanced as shown below: 0 1 33108 673 I have tried SMOTE to balance the dataset, as shown below: ...
4
votes
0answers
222 views

Zero inflated and hurdle models - is it common do 'build your own' with e.g. ensemble model?

I have been given a new analytics problem to solve. The context is app analytics where we would like to predict total revenue per app install after 30 days from install based on just 7 days of data. I....
0
votes
0answers
29 views

After applying SMOTE, the class distribution doesn't match the real world. Is this a problem? [duplicate]

I have an extremely unbalanced dataset with two classes: 1: 1,800 # class 1 0: 40,000 # class 0 This is real world customer data of churned/not churned If I ...

1
3 4
5
6 7
18