New answers tagged

0

Everybody understands how to perform $k$-fold cross-validation but there is often quite a lot of confusion about where/how to use it. So thanks for this good question :) First, cross-validation is a statistical method for evaluation, not for training: Of course training is performed during cross-validation, but it is performed $k$ times and therefore there ...


0

It depends how you want to cluster the data, but here are some options.... FEATURE ENGINEERING You could, for example, completely ignore the timestamps and just seek to cluster the different modes of operation are based on the magnitude of the feature alone. Here, simply extract the values into a new feature list. Otherwise, you have to consider what is ...


0

If you have many available input parameters/features (financial data like balance, depreciations, tax for several years for several companies, the business areas where those companies are working in (e.g. telco, banks, media, etc) and you already have "labelled" data (I mean, you already have the "tax" saving for you previous customers)......


1

To be clear, do you think the data could be distributed according to a particular probability distribution? If so you should model it directly without a neural network. Your model parameters are simply the parameters of that probability distribution ($\mu$ and $\sigma^2$ for a gaussian, $\lambda$ for a poisson etc.,). If you think your data is distributed ...


1

It would depend on the approach you want to take... Based on the information you gave, I could imagine turning the data into a classification problem, whereby you cluster in the feature space of the various customer profile features. You could train the classifier on a "did buy"/"didn't buy" column. The descriptive statistics you ...


1

You can separate both the continuous and categorical features. Then use pd.get_dummies() to encode the categorical features and convert them into a form that is understood by model. Model Doesn't understand Strings, you need to pass the values as numeric. continuous =[features for features in df.columns if df[features].dtype!='O'] # create continuous ...


1

The issue is that logistic regression cannot make use of features which are strings. To use these features in your model you have to convert them to values first by encoding them. There are several ways of encoding the string values into numerical values, examples of this are using a LabelEncoder, OneHotEncoder, and OrdinalEncoder.


0

I assume Renewals/Cancellations are your expected output, so it can be considered as a binary classification. From where I stand, all you mentioned (policies) in your first paragraph is meaningless because I cannot see how I can use them to build any model. Rather, you better study what the clients who used to renew/cancel respectively look like. And that is ...


2

One option would be to transform the y / target variable to be distributed more like a Gaussian, the most common transformations are log and quantile transformation. Gaussian transformation often increases the model fit statistics.


2

Taking the difference (ie speed1-speed2) as the target variable effectively dismisses any low-frequency variablitiy and targets only high-frequency variability, even noise. One approach would be to bin the (highly-variable) target variable into fixed range bins and take the mid point (or any other fixed point) of each bin as the new target (stabilised) ...


1

Use a LSTM, where the input is a sequence, specifically the sequence of records for that patient. You can train the LSTM to predict anything you want -- e.g., the next step. In LSTMs, the sequence normally is fixed-length (the same length for all people; you pad shorter sequences); each element of the sequence is a feature vector of same length (the same ...


0

Your model is decent. Predictions are better than random chance. Macro average is a simple average of the performance measures (precision, recall etc) across all classes/labels. Micro average is a weighted average of the same , where the weights are based on the number of samples per class/label (support column).


0

Actually, your objective here is not clear. Following your example, I belive you want to obtain likeness/relationship between users and places. So basically what you would want to do is to create a domain of users and places. Now for different addresses (eg. A and C), you can treat the same user (eg. One) as different users i.e. "One-A" and "...


0

You can use seller mean buying price, std buying price, max buying price, min buying price, median buying price PLUS include recently user buying power to suggest the totally new product to the user given the current data that's best I can recommend although extensive data can lead to better suggestions.


Top 50 recent answers are included