This document describes a project to build a machine learning model for predicting laptop prices. It involves collecting a dataset of laptop specifications and prices, analyzing the data, developing predictive models using techniques like linear regression and random forests, and creating a web application using Flask that allows users to input laptop features and receive predicted prices. The project aims to help consumers and retailers make more informed purchasing and pricing decisions. Future work may include incorporating real-time data streams, enhancing the ML models, and obtaining user feedback to improve accuracy.
Bridge Fight Board by Daniel Johnson dtjohnsonart.com
Laptop Price Prediction Using ML
1. “Laptop Price Prediction Using Machine Learning”
A MINOR PROJECT
Submitted in Partial Fulfillment of the Requirement for the Award of the Degree of
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE & ENGINEERING
SUBMITTED TO
LNCT UNIVERSITY
Bhopal (M.P.)
2. SUBMITTED BY:
Ayaan Qureshi (LNCBBTCSE036)
Ashutosh Chouhan(LNCBBTCSE034)
Ritesh Kaithwas (LNCBBTCSE095)
LNCT UNIVERSITY, Bhopal (M.P.), India
APPROVED BY:
Dr. Megha Kamble
PRINCIPLE NAME:
Dr. Soni Changlani
UNDER THE SUPERVISION OF:
Prof. Shailendra Chourasia
School of Computer, Science & Technology
LNCT UNIVERSITY, Bhopal (M.P.), India
School of Computer, Science & Technology
LNCT UNIVERSITY, Bhopal (M.P.)
Session: June 2023
3. Contents
• Introduction
• Motivation
• Problem Statement
• Objectives
• Literature Survey
• System Architecture
• System Design
• System Implementation
• Results
• Conclusion
• Future Work
• References
2
4. • The laptop market has been growing steadily for years, even before the global pandemic. According to a
study conducted by Statista, the revenue of the notebook market segment continued to grow and reached
$140 billion in 2020, compared to $132 billion in 2018. The growth is due to the widespread use of laptops
in various fields. In recent years, the demand for laptops has increased, mainly due to the growth of remote
work, distance learning and the growing gaming industry. As more and more people use laptops in their
daily activities, the market has become more competitive, leading to significant differences in laptop prices.
• Price differences between online stores and brick-and-mortar stores became evident when the same
wearable model is sold at significantly different prices. This has created a challenge for consumers who
may overspend on cheaper products or miss out on better deals elsewhere
Introduction
5. • Ability of consumers to make informed purchasing decisions.
• Improve user experience by simplifying price comparison.
• To help users in planning the budget for the purchase of a laptop.
• Providing market analysis to manufacturers and retailers.
• Acts as a learning tool to understand price dynamics.
• Proposing a personal project or business opportunity.
A laptop price predict website provides benefits such as consumer empowerment, user experience
improvement, budget planning support, market insight, educational purposes, and showcasing personal
projects or business opportunities.
Motivation
6. • The problem is creating a predictive model that can accurately estimate the price of a laptop based on its features
and specifications. This helps both buyers and sellers as buyers can use predicted prices to compare different laptops
and make informed purchasing decisions. Sellers can use it to price their laptops competitively in the market.
• The dataset provided for this task includes various characteristics of laptops such as brand, processor, RAM,
graphics card, screen size, storage capacity, and other technical specifications, along with corresponding prices.
increase.
• A model should be trained on this dataset to learn the relationship between these features and laptop prices, and
tested on another dataset to evaluate its accuracy. Model accuracy is measured using metrics such as mean squared
error (MSE) and root mean squared error (RMSE). Lower values for these metrics indicate better performance of
the model in predicting laptop prices.
• Successful implementation of this model will enable buyers and sellers to make better decisions based on accurate
laptop price quotes, resulting in more efficient and transparent market transactions.
Problem Statement
7. • To give consumers a tool that can approximately calculate the price of a laptop based on many aspects
including its characteristics, brand, age, and other pertinent features is the goal of building a website that
predicts the price of laptops.
• The website may be helpful for those wishing to buy or sell laptops as well as for companies in the
computer sector who want to keep up with industry trends and make informed decisions about pricing and
inventory management
Objective
8. Paper Name: Laptop Price Prediction using Machine Learning
Author: Prof. Vaishali Surjuse; Sankalp Lohakare; Aayush Barapatre; Abhishek Chapke
Abstract: This paper presents a Laptop price prediction system by using the supervised machine learning
technique. The research uses multiple linear regression as the machine learning prediction method which
offered 81% prediction precision. Using multiple linear regression, there are multiple independent variables but
one and only one dependent variable whose actual and predicted values are compared to find precision of
results. This paper proposes a system where price is a dependent variable which is predicted, and this price is
derived from factors like Laptop’s model, RAM, ROM (HDD/SSD), GPU, CPU, IPS Display, and Touch
Screen.
Literature Survey
9. Paper Name: Laptop Prediction & Comparison using Machine Learning
Author: Prof. Parmeshwar Manegopale, Komal Nerpagar, Sanal Sawant, Madhuri Shinde, Kunal Chindarkar
Abstract: The laptop price predictor project is a project that aims to predict the price of laptops. The project will be
divided into 3 parts, each having its own specific tasks. The first part is to create a model that predicts the price of
laptops based on various factors such as the size of screen and CPU speed. The second part is to test this model on real
data collected from different websites. Finally, the third part is to present our results and discuss how we built this
model in order to make it more accurate. Laptop price predictor is a tool which predicts the price of laptops. It consists
of a series of algorithms that predict the price of laptops on the basis of their features and specifications. The results
obtained by this project are in close agreement with those obtained using other prediction methods such as neural
network and support vector machine (SVM).
Literature Survey
10. Paper Name: Stock Market Price Prediction Using Random Forest And Support Vector Machine
Author: R S Abirami , K.Varalakshmi , Maddika Jaswanth Reddy , Kota Venkata Madhava Reddy , Chittipi
Reddy Akash
Abstract: In the past decades, there is an increasing interest in predicting markets among economists,
policymakers, academics and market makers. The objective of the proposed work is to study and improve the
supervised learning algorithms to predict the stock price. Stock Market Analysis of stocks using data mining
will be useful for new investors to invest in stock market based on the various factors considered by the
software. Stock market includes daily activities like Sensex calculation, exchange of shares. The exchange
provides an efficient and transparent market for trading in equity, debt instruments and derivatives. Our aim is
to create software that analyses previous stock data of certain companies, with help of certain parameters that
affect stock value. We are going to implement these values in data mining algorithms and we will be able to
decide which algorithm gives the best result. This will also help us to determine the values that particular stock
will have in near future. We will determine the patterns in data with help of machine learning algorithms.
Literature Survey
18. Step 1 : Let's import the libraries and load our data into the Jupyter Notebook. Data is an essential component of machine
learning. There are a few more things to consider after we've examined the head, shape, information, any NULL values, and
duplicate values.
System Implementation
20. Step 3: Exploratory Data Analysis
Understanding data is the process of exploratory analysis. It aids in the identification of features and patterns that can be
utilized by machine learning algorithms. You can make better decisions and eliminate a lot of guesswork by recognizing
trends and commonalities in your data.
The distribution of the target variable is skewed and it is obvious that low-price commodities are sold rather than branded
ones.
22. Type of Laptop
We can check which type of laptop is available like a gaming laptop, workstation, or notebook. Major people prefer laptops
because they are under budget and the same can be concluded from our data.
25. Price with Ram
Again Bivariate analysis of price with Ram. If you observe the plot then Price is having a very strong positive correlation
with Ram or you can say a linear relationship.
26. Step 4: Modeling
We have imported libraries to split data, and algorithms you can try. At a time we do not know which is best so we can try all
the imported algorithms
30. Exporting the Model
Now we are done with modeling. we will save the pipeline object for the development of the project website. We
will also export the data frame which will be required to create dropdowns on the website.
31. Step 5: Creating A Web Application For Laptop Price Prediction Model
Flask is a lightweight and flexible Python web framework that provides powerful tools for building web
applications, including a laptop price prediction website
35. In conclusion, a laptop price forecast website provides valuable insights and predictions about laptop price trends
in the market. By analyzing historical data, market conditions and various factors affecting laptop prices, the site
aims to help consumers, retailers and manufacturers make informed decisions.
The website uses advanced algorithms and machine learning techniques to analyze large volumes of data and
generate accurate predictions. However, it is important to note that these projections are based on historical trends
and market conditions and may not take into account unexpected events or disruptions in the industry
Conclusion
36. 1. Incorporating real-time data: To improve the accuracy of forecasts, the site can explore the integration of real-
time data streams
2. Enhanced Machine Learning Models: Continuous improvement and optimization of the machine learning
models used to predict price can improve accuracy
3. User Feedback and Reviews: Integrating user feedback and reviews into predictive models can help capture
laptop users' opinions and preferences
4. Partnerships with manufacturers and retailers: Partnerships with laptop manufacturers and retailers can provide
additional information and insights
Future Work
37. [1] International Journal of Computer Science and Mobile Computing. Laptop Price Prediction using Machine Learning.
[2] https://www.researchgate.net/publication/ 50946368_Exploratory_data_analysis_in_the_
context_of_data_mining_and_resampling.
[3] https://www.academia.edu/69591584/Laptop_Price_Prediction_using_Machine_Learning
[4] https://medium.com/analytics-vidhya/laptop-price-prediction-by-machine-learning-7e1211bb96d1
[5] https://www.digitalocean.com/community/tutorials/how-to-make-a-web-application-using-flask-in-python-3
[6] https://www.kaggle.com/datasets/muhammetvarl/laptop-price
References