1 minute read
International Journal for Research in Applied Science & Engineering Technology (IJRASET)
ISSN: 2321-9653; IC Value: 45.98; SJ Impact Factor: 7.538
Advertisement
Volume 11 Issue I Jan 2023- Available at www.ijraset.com
User profiles are built on data derived from user actions such as: Purchases, ratings (likes and dislikes), downloads, items searched on the website and/or items placed in shopping carts, and clicks on product links. Let's say you have just purchased a smartphone from your website and want to recommend accessories to users who have previously purchased smartphone accessories. In addition to keywords such as smartphone make, brand, and model, user profiles indicate that previous purchases included previous purchases included phone owners with credit card cases. Based on this information, the recommendation system can suggest similar phone mounts for new phones with attributes such as an RFID blocking fabric layer to help prevent fraudulent credit card scans. In this example, the user would expect similar cell phone recommenda - tions, but the RFID blocking feature could be an unexpected but welcome feature nonethless .
A. Code and execution
1) Import the dependencies
2) Data collection and pre-processing(loading the data from csv file to pandas dataframe).
3) Selecting the relevent features for recommendation.
4) Replacing the null values with null string.
5) Combining all the selected features.
6) Converting the text data to featurr vectors.
7) Getting the similarity scores using cosine similarity.
8) Getting the movie name from the user.
9) Creating a list with all the movie names given in the dataset.
10) Finding the close match for the movie name given by the user.
11) Finding the index of the movie with title.
12) Getting a list of similar movies based on index value.
13) Sorting the movies based on their similarity scare. Print the name of similar movies(30) based on the index.
