Student: Stanley

Facebook Volume Prediction

Need to do the below for a given data set 4. DATA PRE-PROCESSING.................................................................................................................... 4.1 Variable Data Type Transformation:............................................................................................. 4.2 Removal of unwanted variables:.................................................................................................. 4.3 Missing Value Treatment:............................................................................................................ 4.4 Data split into test and train:........................................................................................................ 4.5 Outlier treatment:....................................................................................................................... 5. ANALYTICAL APPROACH:.................................................................................................................. 5.1 Model Building, Validation and Tuning.......................................................................................... 6. MODELLING PROCESS....................................................................................................................... 7. MODEL COMPARISONS.................................................................................................................... 1. Feature Selection using different methods:................................................................................... 2. Model Comparison after Feature Selection:................................................................................... 3. Model Comparison after Dimension Reduction: For both small businesses and large corporations, social media is playing a key role in brand building and customer communication. Facebook is the social networking site relevant for firms to make themselves real for customers. Just to put things in context, the advertising revenue of Facebook in the United States in 2018 stands up to 14.89 billion US dollars. The advertising revenue outside the United States comes down to 18.95 billion US dollars. Latest research reports have indicated that user generated content on facebook drives higher engagement than ads. The amount of data that gets added to the network increases day by day and it is a gold mine of researchers who want to understand the intricacies of user behavior and user engagement. In this Hackathon, we discuss one such problem where we take a step towards understanding the highly dynamic behavior of users towards facebook posts. The goal is to predict how many comments a user generated posts is expected to receive in the given set of hours. We need to model the user comments pattern over a set of variables which are provided and get to the right number of comments for each post with minimum error possible.

Budget: $17.00

Due on: April 30, 2020 00:00

Posted: 6 months ago.

Answers (0)