71.SMART CAMPUS PLACEMENT SYSTEM.pptx71.SMART CAMPUS PLACEMENT SYSTEM.pptx

71.SMART CAMPUS PLACEMENT SYSTEM.pptx71.SMART CAMPUS PLACEMENT SYSTEM.pptx

1. Department of Computer Science & Engineering A Major Project Presentation           on SMART CAMPUS PLACEMENT SYSTEM USING ML Internal Guide Dr. Sheo Kumar , Professor & H.O.D , Department of CSE BY Asutosh Tripathy (228R1A0572) Chamala Pallavi (228R1A0581) Chidipothu Mahesh (228R1A0584) Batch No: B10

2. Abstract The Smart Campus Placement System is a web-based application developed using the Django framework to enhance and automate the college recruitment process. The system aims to bridge the communication gap between students, placement officers, and recruiting companies by providing a centralized platform for managing placement activities efficiently. Companies can also register on the platform, list available positions, define eligibility criteria, and view applicants.

3. Introduction Campus placements play a crucial role in shaping the careers of students by providing them with opportunities to work with leading organizations directly from their educational institutions. However, the traditional placement process is often tedious, time-consuming, and prone to human error due to its manual nature. Coordinating among students, placement officers, and companies can become overwhelming, especially in institutions with large student populations. To address these challenges, the Smart Campus Placement System is proposed as a digital solution built using the Django web framework.

4. Existing System The traditional campus placement system in many educational institutions is predominantly manual, involving substantial paperwork and time-consuming coordination among placement officers, students, and companies. Students are usually informed about job opportunities through notice boards, emails, or word of mouth, which can lead to delays and miscommunication. Maintaining student records, resumes, and academic details in physical files or basic spreadsheets often results in data redundancy, loss, and inefficiency.

5. Limitations of Existing System Requires stable internet connection for access and operation. Initial setup and deployment may be time-consuming for institutions unfamiliar with web technologies. Limited accessibility for users without digital literacy or device access. Security threats if not properly maintained (e.g., SQL injection, data breaches). System performance may degrade with high user load if not optimized. No offline mode for data entry or access.

6. Proposed System The Smart Campus Placement System is a web-based solution designed to automate and optimize the entire campus recruitment process. In the proposed system, students can register, update their profiles, upload resumes, and apply for job opportunities based on automatically verified eligibility criteria. Placement officers can manage student data, post job openings, monitor applications, schedule interviews, and generate placement reports. Recruiters are given access to view eligible candidates, post vacancies, and coordinate interviews — all through a secure, user-friendly interface.

7. Advantages of Proposed System Efficiency : Reduces manual work and speeds up the recruitment process. Accuracy : ML algorithms reduce errors in candidate-job matching. Transparency : All stakeholders can track the process in real time. Scalability : Cloud-based architecture can handle increasing data loads. Data-Driven Decisions : Predictive analytics improve placement success rates.

8. HARDWARE REQUIREMENTS   Processor : Intel Pentium IV / Dual Core / i3 or above Hard Disk : Minimum 120 GB storage RAM : Minimum 4 GB (8 GB recommended for ML model training) Network : Stable internet connection for cloud operations   SOFTWARE REQUIREMENTS   Operating System : Windows / Linux / macOS Programming Languages : Python (ML models), HTML, CSS, JavaScript (frontend) Frameworks : Django / Flask (Backend), Scikit-learn / TensorFlow / PyTorch (ML) Database : MySQL / PostgreSQL / MongoDB Other Tools : Jupyter Notebook, Pandas, NumPy, Matplotlib, Git

9. Modules Student Module TPO Module Recruiter Module Machine Learning Module Notification & Communication Module

10. Libraries used Pandas + NumPy → Handle student datasets and company criteria. Scikit-learn → Predict student placement probability. Flask/Django → Build the smart placement web app. Matplotlib/Seaborn → Visualize placement trends. PyMySQL → Store and fetch student, recruiter, and placement records.

11. Algorithms and Techniques used Collaborative Filtering or Content Based Filtering: To predict and suggest best fit companies for students based on their academic marks, skills, and job requirements. Feedback Analysis Algorithm Sentiment Analysis: To evaluate student feedback and extract insights for TPOs to enhance student support and training. Natural Language Processing (NLP): For processing the textual feedback and categorizing it into actionable recommendations. Skill Compatibility Matching Algorithm: A matching algorithm that cross references company job requirements with student skills and qualifications to shortlist candidates for potential hiring.

12. Literature Survey S.No Title Journal Year Description 1 Student Placement Analysis using Machine Learning IEEE ICCES 2024 2024 Proposed ML models to predict student placement chances using academic and assessment data. Random Forest achieved best accuracy; hybrid models suggested. 2 On-Campus Student Recruitment Analysis using ML Techniques IEEE CONECCT 2024 2024 Automated candidate shortlisting by matching student profiles with company needs using ML ranking. Reduced recruiter effort significantly. 3 Student Placement Probabilistic Assessment Using EQ & ML IEEE Access 2023 2023 Introduced Emotional Quotient (EQ) in placement prediction. Combining academic + soft-skill features improved accuracy and calibration. 4 Predictive Analysis of Internship & Job Placement Success IEEE COMPAS 2024 2023 Built predictive pipeline to forecast internship/job placement success. Found internship experience and domain courses as strongest predictors. 5 Comparative and Ensemble ML Approaches for Student Placement Prediction IEEE Access / Survey 2023 Compared multiple ML classifiers and ensemble techniques. Ensemble and explainable AI methods achieved highest accuracy for placement prediction.

13. System Architecture

14. Conclusion Traditional placement methods and existing digital systems are inefficient, error-prone, and lack scalability or full stakeholder integration. The proposed Smart Campus Placement System addresses these issues using Django, offering automation, role-based access, eligibility verification, scheduling, and real-time updates. The literature review justifies the need for this centralized, secure, and efficient system to enhance transparency and improve the placement process.

15. THANK YOU