I would like to propose that the Help Center topic What topics can I ask about here? be eddited to the following:

What topics can I ask about here?

Please look around to see if your question has been asked before. It’s also OK to ask and answer your own question.

This is a list of what is on topic on Data Science Stack Exchange:

Data Science can be described as the integration of Machine Learning (Math and Statistics) and Programming with the Knowledge of a Specific Field to find and visualize solutions in that Field using Data.

Machine Learning Topics:

  • Questions on pros and cons of certain Machine Learning models. Example:

    • What are the benefits of using GELU and Leaky-RELU over RELU for object detection?
  • Questions on feature engineering, feature selection and dimensionality reduction. Example:

    • When is it suitable to apply L1 regularization for feature selection?
  • Questions for recommendation on models for specific problems. Example:

    • Given Facebook Likes, is there an ML technique to predict age and gender?

Programming related to datascience:

  • Questions on the pros and cons in the use of libraries, languages or frameworks for Data Science. Example:

    • When executing an ARIMA model in Spark, what are the pros and cons of using Python instead of R?
  • Question on the available implementations for given models. Example:

    • Where can I find a C implementation of CNNs for mobile devices?

Data Visualization and Explanation:

  • Question of best practices and best ways to visualize certain kind of data. Example:
    • I would like to produce a infographic on the 'Brexit' referendum. Given public opinion data across the UK, what are some meaningful techniques to visualize it in a dashboard?

Field Specific information with direct relation to Data Science:

  • Questions of field understanding that can be used for modeling. Example:
    • What Image Processing procedures may help solving object detection in dark environments?

Questions on Data Science

  • Career related, definitions and interpretations of terms in Data Science

For off-topic questions

If your question is not specifically on-topic for Data Science Stack Exchange, it may be on topic for another Stack Exchange site. For example, questions here are frequently also suitable, or more suitable, on one of:

If no site currently exists that will accept your question, you may commit to or propose a new site at Area 51, the place where new Stack Exchange communities are democratically created.

Edit: Examples removed to reduce size:

  • While using Keras, my model crashes and gives me this exception
  • Is it possible to implement a LSTM on a device with 128 KB of memory?
  • Given process monitoring data arriving every 10ms, what statistical tool should - I use to best characterize a change in the process - mean? a distribution?
  • How can I encode text for regression algorithm
  • Which kind of algorithm is usually better for tabular data? Neural Networks of Decision Trees?
  • What are the benefits of using CNNs instead of Recursive layers to deal with spatially related data?
  • 2
    $\begingroup$ This is the correct place to propose the change since mods can edit that page, and also the correct place to discuss the proposal if some users disagree/want to give feedback/improvement. $\endgroup$
    – Andrew T.
    Apr 20, 2019 at 5:39
  • 1
    $\begingroup$ good stuff thank you! more feedback from others would be appreciated :-) I think it might be a little bit long for some people's attention span. can we make it more crisp? $\endgroup$
    – oW_ Mod
    Apr 22, 2019 at 16:13
  • $\begingroup$ Maybe using just 1 example per topic $\endgroup$ Apr 22, 2019 at 17:26


You must log in to answer this question.

Browse other questions tagged .