Skip to main content
21 votes

What would I prefer - an over-fitted model or a less accurate model?

There are a couple of nuances here. Complexity question very important - ocams razor CV - is this trully the case 84%/83% (test it for train+test with CV) Given this, personal opinion: Second one. ...
Noah Weber's user avatar
  • 5,709
15 votes

What would I prefer - an over-fitted model or a less accurate model?

It depends mostly on the problem context. If predictive performance is all you care about, and you believe the test set to be representative of future unseen data, then the first model is better. (...
Ben Reiniger's user avatar
  • 12k
11 votes
Accepted

Neural network with flexible number of inputs?

Yes this is possible by treating the audio as a sequence into a Recurrent Neural Network (RNN). You can train a RNN against a target that is correct at the end of a sequence, or even to predict ...
Neil Slater's user avatar
  • 29.1k
10 votes
Accepted

Is max_depth in scikit the equivalent of pruning in decision trees?

Is this equivalent of pruning a decision tree? Though they have similar goals (i.e. placing some restrictions to the model so that it doesn't grow very complex and overfit), ...
Djib2011's user avatar
  • 7,998
9 votes

What would I prefer - an over-fitted model or a less accurate model?

The first has an accuracy of 100% on training set and 84% on test set. Clearly over-fitted. Maybe not. It's true that 100% training accuracy is usually a strong indicator of overfitting, but it's ...
Ray's user avatar
  • 191
9 votes
Accepted

Why does data science see class imbalance as a problem for supervised learning when statistics does not?

It's generally not related to Data Science but what goes around; typically all sort of bad practice relating to laziness / looking for short term rewards. I wouldn't say DS is pushing for it but ...
Lucas Morin's user avatar
  • 2,309
8 votes
Accepted

Ideas for prospect scoring model

I faced almost exactly the same scenario a year and a half ago -- basically what you have is a variation of the one-class classification (OCC) problem, specifically PU-learning (learning from Positive ...
Brandon Loudermilk's user avatar
8 votes
Accepted

What is deconvolution operation used in Fully Convolutional Neural Networks?

Upsampling layer is used to increase the resolution of the image. In segmentation, we first downsample the image to get the features and then upsample the image to generate the segments. For ...
Yash Katariya's user avatar
8 votes

Why neural networks do not perform well on structured data?

... someone pointed out that neural networks do not work very well with the structured data (data in tabular format) as compared to the unstructured data (like representing each pixel in an image). ...
Rob's user avatar
  • 513
8 votes
Accepted

Is there any difference between a weak learner and a weak classifier?

A weak learner can be either a classification or a regression algorithm: Boosting (Schapire and Freund 2012) is a greedy algorithm for fitting adaptive basis-function models of the form in ...
Jonathan's user avatar
  • 5,430
7 votes

How to tell if a problem should use regression or classification model?

A good rule of thumb is to look at the level of measurement of the target/response variable. If the response is measured on a nominal scale, the problem is a classification problem. Values on a ...
Johan Falkenjack's user avatar
7 votes

time series forecasting - sliding window method

Try this: Make the data stationary (remove trends and seasonality). Implement PACF analysis on the label data (For eg: Load) and find out the optimal lag value. Usually, you need to know how to ...
Aniruddh Goteti's user avatar
7 votes
Accepted

Why is there a trade-off between bias and variance in supervised learning? Why can't we have best of both worlds?

The tradeoff between bias and variance summarizes the "tug of war" game between fitting a model that predicts the underlying training dataset well (low bias) and producing a model that doesn't change ...
aranglol's user avatar
  • 2,206
7 votes
Accepted

Why models performs better If normalize test data and train data separately?

If apply normalization on training and testing in a separate way, I get really good results 85% (and sometimes more) and the further steps I try to do next work better as well. The problem with ...
Erwan's user avatar
  • 25.6k
6 votes
Accepted

Why will the accuracy of a highly unbalanced dataset reduce after oversampling?

Imagine that your data is not easily separable. Your classifier isn't able to do a very good job at distinguishing between positive and negative examples, so it usually predicts the majority class for ...
timleathart's user avatar
  • 3,940
6 votes

Why will the accuracy of a highly unbalanced dataset reduce after oversampling?

Accuracy is probably not a good metric for your problem. For the original dataset, if the model just makes a dummy prediction that all samples belong to the bigger class, the accuracy will be 83% (...
TQA's user avatar
  • 536
6 votes

Confused about the different aspects in Machine Learning

Good question and welcome to Datascience Imagine you have the tree as follows. ...
alpha_989's user avatar
  • 161
5 votes
Accepted

Which supervised learning algorithms are available for matching?

You can try to frame this problem as a recommender systems situation. Where you have your users (prospective students) and items (alumni) and want to recommend to the users one item. It's not a ...
João Almeida's user avatar
5 votes

Binary Classification

Looks like to me this is a classic imbalance binary classification problem (see comments above). What loss are you using ? It looks like your model is predicting the non-membership class because it’s ...
Alexis's user avatar
  • 178
5 votes
Accepted

which metric is better for boosting methods

Depends. The first thing that has to be clear is that you are running an experiment, which means you need to measure both with the same metric. Which one? Depends on which underlying problem you are ...
Juan Esteban de la Calle's user avatar
5 votes

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

Audio .wav codec file has a 44 byte header which will give you critical data like bit depth ( CD quality audio is 16 bits per sample), sample rate ( CD quality uses 44,100 audio samples per second ), ...
Scott Stensland's user avatar
5 votes
Accepted

Where and how to do large scale supervised machine learning?

First, when working with big data most of the time it's more convenient to work with a random subset rather than the whole thing: usually during the design and testing stages there is no need to work ...
Erwan's user avatar
  • 25.6k
4 votes

generalized likelihood ratio test (GLRT)

Likelihood-ratio tests are a mainstay of classical hypothesis testing. The idea is to form the likelihoods of the two hypotheses under consideration, and choose the one with the highest likelihood if ...
Emre's user avatar
  • 10.5k
4 votes

Regarding "modification" of feature columns in supervised learning

I think what you're talking about is called compound features, and it's extremely important because sometimes it captures interactions between certain features which are not readily apparent in ...
PSub's user avatar
  • 712
4 votes

How to classify a data as not matching any label

Let's phrase it another way, decomposing into two problems: given a sound, we want to know if it's of class A given a sound, we want to know if it's of class B This way of putting it is valuable to ...
Mephy's user avatar
  • 937
4 votes
Accepted

How does KNN handle categorical features

It doesn't handle categorical features. This is a fundamental weakness of kNN. kNN doesn't work great in general when features are on different scales. This is especially true when one of the 'scales'...
tom's user avatar
  • 2,248
4 votes

Is NN with no hidden layer is behave like a regression?

You would then call it perception model. As in 1945 or so some researcher did this with no hidden layer. They came up with AND,OR,XOR problem where you can solve AND,OR with a single perception model ...
Amin Pial's user avatar
  • 165
4 votes

Is NN with no hidden layer is behave like a regression?

For your first problem, NN without hidden layer is simply linear regression. Of course there is an activation function, but you can use the inverse function of that activation function on your target ...
plpopk's user avatar
  • 178
4 votes

What are the differences between Reinforcement Learning (RL) and Supervised Learning?

What are difference between Reinforcement Learning (RL) and Supervised Learning? The main difference is to do with how "correct" or optimal results are learned: In Supervised Learning, the learning ...
Neil Slater's user avatar
  • 29.1k
4 votes

Why does feature scaling improve the convergence speed for gradient descent?

The answer to this question simply lies in how one performs or applies the chain rule of differentiation. To understand this, first look at back-propagation which is simply a method to update weights ...
khwaja wisal's user avatar

Only top scored, non community-wiki answers of a minimum length are eligible