About the data

There are 25 independent features and 1 dependent features in the dataset. You can download the datasets from the given links:

train - You can download train dataset from here. Use this data to build machine learning model.
test - You can download test dataset from here. Predict the target values for this data using the model you built with the train data.
sample_submission: This is a csv file that contains the sample submission for the challenge. You can download the file from here.

Data Description

Term	Description
userId	Unique number given to each user.
tier	Tier of the city in which the user is residing.
gender	Categorical feature representing the gender of the user. 1 represents male and 2 represents female.
following_rate	Number of accounts followed by the user(feature is normalized)
followers_avg_age	Average of age groups of all the followers of the user.
following_avg_age	Average of age groups of all the accounts followed by the user.
max_repetitive_punc	Maximum repititive punctuations found in the bio and comments of the user.
num_of_hashtags_per_action	Average nubmer of hashtags used by the user per comment.
emoji_count_per_action	Average number of emojis used by the user per comment.
punctuations_per_action	Average number of punctuations used by the user per comment.
number_of_words_per_action	Average number of words used by the user per comment.
avgCompletion	Average watch time completion rate of the videos.
avgTimeSpent	Average time spent by the user on a video in seconds.
avgDuration	Average duration of the videos that the user has watched till date.
avgComments	Average number of comments per video watched.
creations	Total number of videos uploaded by the user.
content_views	Total number of videos watched.
num_of_comments	Total number of comments made by the user (normalized)
weekends_trails_watched_per_day	Number of videos watched on weekends per day.
weekdays_trails_watched_per_day	Number of videos watched on weekdays per day.
slot1_trails_watched_per_day	The day is divided into 4 slots. This feature represents the average number of videos watched in this particular time slot.
slot2_trails_watched_per_day	The day is divided into 4 slots. This feature represents the average number of videos watched in this particular time slot.
slot3_trails_watched_per_day	The day is divided into 4 slots. This feature represents the average number of videos watched in this particular time slot.
slot4_trails_watched_per_day	data
avgt2	Average number of followers of all the accounts followed by the user.
age_group	This is a categorical feature denoting the age of the user. Age of users is divided into 4 groups, 1: <18y; 2: 18-24y; 3: 24-30y; 4: >30y

Saving Prediction File & Sample Submission

You can find more details on how to save a prediction file here: https://discuss.dphi.tech/t/how-to-submit-predictions/548

Sample submission: You should submit a CSV file with a header row and the sample submission can be found below.

prediction

1

2

3

1

4

1

2

Etc.

Note that the header name should be prediction else it will throw an evaluation error.

Cascade Cup Data Science Hackathon

Challenge Starts

Registration Ends

Challenge Ends