COLLEGE OF COMPUTING

AND INFORMATICS

DEPARTMENT OF SOFTWARE

ENGINEERING

ARTIFICIAL INTELLIGENCE PROJECT

Title: Explore Software Engineering Salary Web App

Submitted To Dr. Abdulgany K.

Name Of Students:------------ID
Yaduma Lechisa--------------------------2817/13
Gazu Lemi----------------------------------1260/13
Kengitan Kebeto-------------------------1596/13
Lemesa Kasim----------------------------1680/13
Elias Asefa---------------------------------0917/13
Contents
Documentation ............................................................................................................................................. 2
1. Introduction .......................................................................................................................................... 2
2. Application Overview ............................................................................................................................ 3
a. Country Selection .............................................................................................................................. 3
b. Education Level and Experience Input .............................................................................................. 3
c. Salary Prediction................................................................................................................................ 4
3. Machine Learning Model ...................................................................................................................... 4
a. Dataset .............................................................................................................................................. 4
b. Feature Engineering .......................................................................................................................... 5
c. Model Training .................................................................................................................................. 5
d. Model Evaluation .............................................................................................................................. 5
4. Deployment........................................................................................................................................... 6
a. Front-end Development .................................................................................................................... 6
b. Back-end Integration......................................................................................................................... 6
c. Deployment to a Web Server ............................................................................................................ 7
5. Application Benefits .............................................................................................................................. 7
a. Salary Exploration ............................................................................................................................. 7
b. Employer Insights .............................................................................................................................. 8
c. Decision Support ............................................................................................................................... 8
6. Conclusion ............................................................................................................................................. 9
Screenshots Of The Project ..................................................................................................................... 10

1|Page
Explore Software Engineering Salary

photo of home page

Documentation

1. Introduction

The "Software Engineering Salary Prediction" project is a web-based

application developed using Streamlit. The purpose of this application is
to predict the salary of software engineers based on their education level
2|Page
and experience in multiple countries. By leveraging machine learning
techniques, the application provides valuable insights for both job
seekers and employers in the software engineering field.

2. Application Overview

The web-based application offers an intuitive and user-friendly interface

that allows users to explore salary predictions for software engineers in
different countries. The main features of the application include:

a. Country Selection

The application provides a dropdown menu where users can select the
country for which they want to obtain salary predictions. It supports
multiple countries, enabling users to explore salary trends across
different regions.

b. Education Level and Experience Input

Users are required to input their education level and years of experience
in the software engineering industry. The education level can range from
high school education to advanced degrees such as master's or doctoral
degrees. The experience input allows users to specify their relevant work
experience in years.

3|Page
c. Salary Prediction

Upon providing the necessary inputs, the application leverages the

underlying machine learning model to predict the salary for the given
country, education level, and experience. The predicted salary is
displayed to the user, providing valuable insights into potential earnings
based on the provided information.

3. Machine Learning Model

The core of the "Software Engineering Salary Prediction" application is

a machine learning model trained on a comprehensive dataset of
software engineering salaries from various countries. The model utilizes
a combination of regression techniques, feature engineering, and
statistical analysis to make accurate salary predictions.

a. Dataset

The dataset used for training the machine learning model consists of
salary information collected from software engineers across different
countries. The dataset includes features such as education level, years of
experience, and corresponding salary values.

4|Page
b. Feature Engineering

To improve the performance of the model, feature engineering

techniques are applied to the dataset. This involves transforming and
encoding categorical variables such as education level and country into
numerical representations that can be effectively utilized by the model.

c. Model Training

The transformed dataset is split into training and testing sets. The
training set is used to train the machine learning model, which learns the
underlying patterns and relationships between the input features and the
target variable (salary). Various regression algorithms, such as linear
regression or decision trees, can be employed for training depending on
the specific requirements of the project.

d. Model Evaluation

The trained model is evaluated using appropriate metrics to assess its

performance and generalization capabilities. Metrics such as mean
absolute error (MAE) or root mean squared error (RMSE) can be used to
measure the prediction accuracy of the model. The evaluation results
guide further improvements and fine-tuning of the model if necessary.

5|Page
4. Deployment

The "Software Engineering Salary Prediction" application is deployed

using Streamlit, a powerful Python library for creating web-based data
applications. Streamlit provides an interactive and responsive interface
that allows users to input their information and obtain salary predictions
in real-time.

To deploy the application, the following steps were followed:

a. Front-end Development

The user interface (UI) of the application was developed using

Streamlit's built-in components and layout features. The UI components
were designed to be visually appealing and easy to navigate, ensuring a
smooth user experience.

b. Back-end Integration

The machine learning model, trained on the software engineering salary

dataset, was integrated into the application's back-end. When a user

6|Page
provides their education level, experience, and country selection, the
model is invoked to predict the corresponding salary.

c. Deployment to a Web Server

The application was deployed to a web server that supports Streamlit

applications. This allows users to access the application through a web
browser without requiring any local installations. The web server
ensures the availability and accessibility of the application to a wide
range of users.

5. Application Benefits

The "Software Engineering Salary Prediction" application offers several

benefits to its users:

a. Salary Exploration

7|Page
Job seekers can utilize the application to explore potential salary ranges
based on their education level and experience in different countries. This
information helps them make informed decisions during the job search
process and negotiate fair compensation.

b. Employer Insights

Employers in the software engineering industry can gain valuable

insights into salary trends for different countries. They can use the
application as a benchmarking tool to determine competitive salary
ranges for their job openings, ensuring they attract and retain top talent.

c. Decision Support

The application serves as a decision support system for both job seekers
and employers. By providing accurate salary predictions, it aids in
making informed decisions related to career choices, job offers, and
salary negotiations.

8|Page
 6. Conclusion

The "Software Engineering Salary Prediction" project is a web-based

application that leverages machine learning techniques to predict
software engineering salaries based on education level and experience in
multiple countries. The application provides valuable insights to job
seekers and employers, helping them navigate the complex landscape of
software engineering salaries.

9|Page
Screenshots Of The Project

10 | P a g e
11 | P a g e
12 | P a g e