Movie-Box-Office-predictor 🎥 💰

Authors:

• Jayant
• Christopher Budd
• Mustafa Syed

Objective:

To predict the box office revenue generated for movies since January 1st, 2015 until 5th November, 2023.

Dataset:

Dataset used: https://www.kaggle.com/datasets/akshaypawar7/millions-of-movies/data

Install: scikit-learn, numpy, matplotlib, pandas, seaborn and xgboost as follows:

• conda install -c anaconda scikit-learn
• conda install pandas
• conda install numpy
• conda install -c conda-forge matplotlib
• conda install seaborn
• pip install xgboost

Tasks:

0. Getting the data
   • Loading the data on your machine
1. Look at the big picture
2. First impressions on the dataset, EDA graphs, and patterns found
3. Preprocessing: preparing the data for the ML algorithms
   • Data cleaning
   • Encoding
   • Feature scaling (re-sampling)
4. Training and evaluation of 3 ML algorithms
   • Algorithms used
   • Training
   • Findings and results comparison
5. Three Graphs for the best performance algorithm
6. Limitations of the model

Appendix 1 :

Code found in the pdf

Appendix 2 :

Github repository link: https://github.com/Jayant1Varma/Movie-Box-Office-predictor.git
Original dataset citation: The dataset used was https://www.kaggle.com/datasets/akshaypawar7/millions-of-movies/data .

Presentation video link: https://youtu.be/R6Qv8SrqOKY

However, this dataset is updated daily, but we used this dataset as it was available on November 5th 2023 You can find the exact dataset we used here: https://drive.google.com/file/d/1uPtHyqpAKkqZUpft8A0FPVXPR2iT32SN/view?usp=sharing It is also available on our github