Mobile Price Prediction - Classification Analysis

📱Content:

The price of a cell phone, which has become a necessity in our daily lives, varies widely depending on its specifications. In this notebook, we will explore the factors that affect cell phone prices and predict new samples based on the best model.

📱This notebook includes the following:

• Preprocessing
• Data cleaning
• Exploratory data analysis (EDA)
• Preparing the data to train a model
• Training and making predictions using various classification models
• Model evaluation
• Using various ensemble learning methods

📱Objective:

Our objective is to predict the price range of a mobile phone by building a model that takes into account various features provided in the dataset. We will be using supervised learning methods such as Decision Trees (DTs), Random Forest, and Support Vector Machine (SVM) to determine the best model for this problem.

📱What Problem We Have?

Our task is to perform a classification on the target variable "Price Range" based on the data and attribute information. To achieve the best possible classification, we will develop a model that accurately predicts the price range of mobile phones.

Kaggle link: Mobile Price Classification

📔About Dataset

Bob, a budding entrepreneur, has taken the bold step of starting his own mobile company. He has set his sights high and wants to challenge big players like Apple, Samsung, and other prominent brands in the mobile phone industry. However, Bob faces a crucial hurdle - he is unsure how to estimate the prices of the mobile phones his company will create.

In a competitive market like mobile phones, assumptions won't cut it. Bob understands this and decides to tackle the issue by collecting sales data on mobile phones from various companies. He hopes to find a correlation between a mobile phone's features, such as RAM, internal memory, etc., and its selling price. However, Bob is not proficient in Machine Learning and requires your expertise to solve this problem.

📔Problem Statement:

The goal of this problem is not to predict the actual price of a mobile phone, but rather to determine a price range that indicates how high the price could be. With your help, Bob can gain a better understanding of the market and set competitive prices for his products.