Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Classify ad interests #10

Open
kaustubhhiware opened this issue Jun 20, 2018 · 5 comments
Open

Classify ad interests #10

kaustubhhiware opened this issue Jun 20, 2018 · 5 comments
Labels
Difficulty: Hard KWoC ML-esque Issues that offer opportunities to apply Machine Learning / Data Science. moonshot Issues we're interested in, but not sure how to approach them,

Comments

@kaustubhhiware
Copy link
Owner

Classify a facebook user's ad interests into categories, say sports, engineering, humor, developing, etc.

This issue has a lot of potential, and is currently only in ideation phase. Please discuss your vision about how / what can be done here.

@kaustubhhiware kaustubhhiware added Difficulty: Hard ML-esque Issues that offer opportunities to apply Machine Learning / Data Science. moonshot Issues we're interested in, but not sure how to approach them, labels Jun 20, 2018
@iriyagupta
Copy link

For classifying ad interests , we can use collaborative filtering here (specifically item based one) since it is basically a recommendation system. We can use scikit for finding similarities.Like if there is a user A and he/she searches or likes posts related to humor then we can create a system where he/she will receive the suggestions based on the tags on the other posts like humor can have tags like comedy , funny , fun etc..

@xprilion
Copy link
Collaborator

@Riya2908 I agree with you. Have you downloaded your fb data in json format and checked the ads interest files? can you chalk about briefly which and how will you be using those files? We'll then assign you the task :)

@xprilion xprilion added the KWoC label Jun 25, 2018
@iriyagupta
Copy link

@xprilion I haven't downloaded my dataset , but we can gather the dataset of any user or find it online.I am not active on much social platforms.
However , I do have some path in my head.I'll jot down the pointers and will send them in slack today.

@xprilion
Copy link
Collaborator

@Riya2908 I suggest you to download your facebook data archive in json format before planning for the solution to this issue. It will help you to develop a solution in sync with the project. do ping in the slack channel for any queries or help you might need.

@iriyagupta
Copy link

@xprilion yes sure.Thanks

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Difficulty: Hard KWoC ML-esque Issues that offer opportunities to apply Machine Learning / Data Science. moonshot Issues we're interested in, but not sure how to approach them,
Projects
None yet
Development

No branches or pull requests

3 participants