Questions tagged [classification]

An instance of supervised learning that identifies the category or categories which a new instance of dataset belongs.

Filter by
Sorted by
Tagged with
1
vote
1answer
20 views

How to approach this multi label classification problem and what will be its accuracy metric?

I have a dataset for people doing trade in various segments (classes) .I am trying to build a multi-label classifier to predict people trading in various segments (classes). My dataset : ...
2
votes
2answers
58 views

Which Technique should we use for predicting an integer output?

I'm working on a problem where my target feature of type integer. i.e (n_clicks). In general, if we want to predict categorical target feature then we use classification algorithms and on the other ...
2
votes
1answer
56 views

How to justify the usage of 200 dimensions in word vectors instead of the 300 dimensions?

When employing machine learning methods in NLP, most of studies use 200 or 300 dimensional vectors. 300 dimensional embeddings carry more information and this, therefore, is considered to produce ...
1
vote
1answer
54 views

Should scaling be done for mixed data (categorical and numerical)?

My dataset contains 13 attributes consisting of 10 Numerical and 3 Categorical attributes and Target. It has 180 observations ...
0
votes
0answers
24 views

How to handle a data set with large number (about 75%) of binary variables?

I am doing a research right now and want to classify (predict) churns of costumers using machine learning. My data set consists of about 500,000 observations with 20 variables: 15 are binary, 2 ...
2
votes
0answers
20 views

Scikit learn - best model to classify supervised two-feature data?

I'm quite new to scikit learn but I am looking for the best approach to go about classifying some data I've collected where each set contains two measurements made over several points of time, along ...
1
vote
0answers
32 views

Classify the input set into categories based on pre-defined rule set

I'm trying to solve a problem where there are 2 input files given, Input 1: A set of strings in the format. All the strings start with "A". A-B-C-D A-B-C-3 A-X-Y-Z-4 A-X-5 A-X-P-Q-R A-X-P-Q-S A-M-9-...
0
votes
1answer
39 views

Understanding python XGBoost model dump output of a very simple tree

I am trying to understand the model dump output from XGBoost. I would like to step through and see exactly how the model arrived at it's prediction. To simplify I trained a model with 1 tree and 1 max ...
1
vote
2answers
54 views

Improving classifcation when some are less represented?

I have a multi-class classification problem. It performs quite well but on the least represented classes it doesn't. Indeed, here is the distribution : And here are the classification results (I took ...
1
vote
0answers
47 views

Big dataset for multi-class classification can't be dasked and split, normal one can't be handled

I have a huge dataframe (550MB), the lending club one available here, and I have to predict the class of the grades. The dask dataframe is : ...
0
votes
1answer
23 views

Keras ANN Trained Model's Accuracy change on prediction

I have trained an ANN Binary classifier using Keras. It gives 90% accuracy. After testing when I predict same data again but pass only one class then accuracy decreases to 40%. I have figured out ...
0
votes
0answers
9 views

Transforming target from object array to integer array to use sparse_categorical_crossentropy for class prediction

I want to do a neural network to predict to which loan class does a borower pertains. There are 6 classes [ A, B, C, D, E, F]. I tried to get rid of the NAs and ...
2
votes
0answers
17 views

Keras model with second to last sigmoid activated Conv1D layer followed by globalMaxPool outputs values outside [0,1]. Why?

I am trying to train a binary classifier. It is a residual network with skip layers etc. but ultimately, the bottom two layers are a 1D convolution with sigmoid activation followed by a global max ...
0
votes
0answers
6 views

How to check if a class segmentation is meaninfull?

Using the Lending Club dataset I have a data frame with the loan characteristics of some borrowers. Here is the distribution of the subgrades: ...
0
votes
1answer
36 views

Churn Prediction Training Set

I don't understand how to form my dataset from activity(logins etc.) and characteristic(location, age etc.) raw user data. Ultimately, each row of the training set will have N activity features for a ...
2
votes
2answers
196 views

Binary classfication vs One-class classification

Why do we need samples of both classes for the training of binary classification algorithms, if one-class algorithms can do the job with only samples from one class? I know that one-class algorithms (...
1
vote
0answers
74 views

Use LightGBM or FFM - imbalanced dataset

I have a highly imabalanced dataset but one that is not sparse. In train there are 1328 positives out of 104000. In validation ...
0
votes
0answers
29 views

BinaryRelevence Classifier giving errors during predicting accuracy scores

I am new to MultiLabel Classification. I have a data set of audio acoustic features and I apply Binary Relevance Algorithm. The output works fine. But when I start calculating the accuracy scores I ...
0
votes
0answers
26 views

Performance of Triplet loss network vs multiclass classification

I am training a triplet loss based classification network and a normal multiclass classification network on some image data. In my case, triplet loss network performs poor than multiclass network. I ...
3
votes
2answers
72 views

How to represent audio data in a format that can be used for preprocessing and modelling?

I have a project that I am working on currently. The project is to classify audio data. The data is in two folders train and test...
2
votes
1answer
96 views

Feature Importance

I have a dataset with 10 features. I've computed the feature importance using permutation importance with cross-validation from eli5, after fitting an extremely randomized trees (ET) classifier form ...
0
votes
0answers
7 views

Loss and accuracy remains constant in time series classification by LSTM

I have a time series data with a classification label of 1 and 0. I am using a LSTM model to classify the series by taking 100 consecutive timestamps as input with a single label. Even after training ...
1
vote
1answer
12 views

adding non-failure data to failure one

I have a dataset containing features of different engines showing when they failed. I want to build supervise learning model to predict whether an engine with a certain mileage is going to fail or not....
0
votes
0answers
11 views

Is it possible to build an intelligent lead classifier with just a few training units

I want to build a lead classifier for my Master Thesis and wanted to ask for an assessment of feasibility. Here are the key points: (1) We have 15 customers and about 100 opportunities of which we ...
1
vote
0answers
120 views

Naive Bayes for Categorical Features (Non Binary)

How do i use Naive Bayes Classifier (Using sklearn) for a Dataset considering that my feature set is categorical, ie more than 2 categories per feature are present. I've looked everywhere, some ...
0
votes
2answers
150 views
0
votes
1answer
214 views

What is the accuracy majority class classifier?

I have an SFrame and a model: ...
0
votes
1answer
28 views

How to implement Classification and Anomaly detection (C++)

I am creating a system using C++(DX11) and i'm reading raw data into my program, i want to classify what the 3D data-set i'm reading in is and detect any anomalies it may have when compared to a ...
1
vote
1answer
63 views

Can I arbitrarily eliminate 20% of my training data if doing so significantly improves model accuracy?

My dataset contains 2000 records with 125 meaningful fields 5 of which are distributed along highly skewed lognormal behavior. I've found that if I eliminate all records below some threshold of this ...
1
vote
0answers
19 views

How can I train a machine learning model with below characterstics? [closed]

Hi I have a classifier model to solve, which has close to 56k samples and 30 features which ...
0
votes
0answers
8 views

How to solve a classification problem with multiple time series?

I am trying to build a model for credit default prediction. I've got a dataset of over 20,000 customers and the features are their payments over the last ≤24 months. The dataset looks like this: <...
0
votes
1answer
34 views

What do we learn from training a dataset for logistic regression

What do we learn from training our dataset in Logistic Resgression? Like in Linear Regression, with the help of training set we are able to generate a best fit line(y = mx+c) where m and c come from ...
1
vote
1answer
13 views

Handling hierarchical category independent variables

I have data with huge categorical attributes. For example, main_column, sub_column1, sub_column2 are 3 hierarchical attributes. If if take dummy variable on these columns the column count is ...
6
votes
1answer
99 views

Why do we use the F1 score instead of mutual information?

We often use the classification threshold that maximizes the F1 score, if we don't have a prior cost function of false positives and false negatives. This balances the desire for precision and recall....
0
votes
1answer
25 views

Has this paper used weighted KNN or not?

Please tell me if you see this paper in the link below has used weighted KNN? because they have used weights as the training and testing samples and no formula written. They don't explain the ...
1
vote
0answers
19 views

Does it make sense to use Transformer encoders on top of a pretrained Word2Vec embedding for a classification task?

As the title says. I am dealing with a text classification task, but I do not have the resources to train a BERT word embedding from scratch. I was thinking of using an existing Word2Vec embedding ...
1
vote
0answers
50 views

XGBoost predicting everything as null when sample weights are passed

I am trying to build an Uplift model using observational data. The data is consists of collections calls to customers and my objective is to predict the incremental probability due to the treatment (...
0
votes
0answers
15 views

Day Classification in Time Series - LSTM

I am working on a problem in which i have a daily time series and I have a label for each day. For simplicity, let's say it is a binary classification, so for each day, there's a label (0 or 1) and 1 ...
3
votes
1answer
77 views

What does high variance mean in a binary classification machine learning model?

My understanding of high variance is that the targets are spread widely around. The output values are "all over the place". In a binary classification model, there can only be 2 outcomes. I am at a ...
0
votes
0answers
12 views

Loss Function for Sparse Sequence Tagging

I'm currently working on trying to classify words in a sentence using bert. Unfortunately the labels I'm using are relatively sparse compared to the full text. Many sentences are only labelled 'O' ...
2
votes
1answer
102 views

How to correctly set a target for a time series based model?

I need help determining the best way to go about creating the target variable for a machine learning model that is trading a financial instrument (stocks, foreign currencies, crpyto, etc). Below is ...
0
votes
2answers
29 views

Extracting tokens from a document: applying Deep Learning or Classification?

I have a legal document from Law. That document is 4-pages of evidence from the plaintiff. I want to identify the Dates, Addresses and Financial transactions in that document. Can I apply deep ...
2
votes
0answers
55 views

Neural network cost is constant never changing during training

I am trying to build a binary classifier to predict a pulsar star with Single Hidden layer Neural Network. But the cost on training dataset after almost 100 iterations has no change, following is the ...
0
votes
0answers
19 views

NLP: Mapping Penn treebank and Brown corpus, to Universal PoS Tags

I am experimenting with NLP and PoS tagging. I wish to build a large corpus, composed of Penn Treebank and Brown corpus, and possibly even more. Unfortunately, their PoS tags are not compatible. Is ...
2
votes
0answers
172 views

Target mean encoding worse than ordinal encoding with GBDT ( XGBoost, CatBoost )

I have a dataset of 23k rows of an unbalanced dataset 85/15 ratio, 10 variables ( 9 of which are categorical ) , i'm using CatBoost and XGBoost for a binary classification. I applied cv (5 iteration ...
0
votes
4answers
70 views

What is the purpose of standardization in machine learning?

I'm just getting started with learning about K-nearest neighbor and am having a hard time understanding why standardization is required. Reading through, I came across a section saying When ...
4
votes
1answer
319 views

How to extract trees in XGBoost?

I want to extract each tree so that I can feed it with any data, and see the output. ...
1
vote
1answer
81 views

Oversampling only balances the training set, what about the testing set?

In a case of imbalanced data classification, I know that we only oversample the training set (to prevent data leakage from training to testing subsets), but what if there are no positive data points ...
2
votes
1answer
53 views

Gradient Boosted Decision Trees How to Find Prediction of Each Tree?

I'm doing a project. I have a classification problem that I should solve using gradient boosted decision trees. What I want to do is create a matrix that gives prediction of each decision tree for ...
2
votes
0answers
34 views

What is the current state-of-the-art video classification technique?

For a project I am aiming to automise the detection of goals in foosball (a.k.a. 'table football') matches. To do so I now track the ball in every frame using the openCV library in Python. To ...