Intelligent Career Path Recommendation System

What the Project Does

The Intelligent Career Path Navigator is an AI-powered Knowledge-Based Expert System (KBS) built on rule-based reasoning. Navigating the modern Information Technology (IT) industry is challenging due to the rapid growth of specialized roles (such as DevOps, AI, Data Science, and Cybersecurity). This system correlates a user's technical competence, soft skills, and personality traits to suggest a personalized IT career path, growth outlook, and learning roadmap.

• Archetype Classification: Analyzes preferred problem-solving styles to categorize the user into 1 of 6 personality archetypes (e.g. Collaborator, Architect, Innovator, Strategist).
• Career Match Scores: Implements pattern matching to evaluate 16 complex questions and outputs the top 3 best-fit IT careers with confidence levels (70% - 95%) and growth rates.
• 3-Phase Learning Roadmap: Automatically generates custom project ideas, courses, and certifications (such as CompTIA, AWS, and Google Career) timeline (3-18 months) for each career.
• Salary Insights: Integrates Malaysia salary scales gathered from JobStreet and MDEC digital economy datasets.

Output Examples & Performance

Below is an example of the rule-based output generated by the CLIPS inference engine for user "Asynawi" based on his answers:

System Inference Results Log

>>> PERSONALITY ARCHETYPE IDENTIFIED:
    The Collaborator (Excellent soft skills, team communication, and logical structure)

>>> RECOMMENDED CAREERS:
    1. AI/Machine Learning Engineer
       - Match Score: 95%
       - Industry Growth: 25% (Very High)
       - Est. Salary: RM 5,000 - RM 35,000+ per month
       - 3-Phase learning roadmap (Months 1-12) generated successfully.

    2. Data Scientist
       - Match Score: 92%
       - Est. Salary: RM 4,000 - RM 25,000+

Interactive CLIPS Inference Engine

Answer 5 profile questions below. Each answer asserts facts into the working memory and triggers rule-based forward chaining — producing your personality archetype and top 3 career matches in real time.

System Design & Inference Workflow

CLIPS Knowledge Inference Tree

Diagram representing the logical reasoning flow. Confirmed user parameters (personality traits, skills, and preferences) are dynamically matched against defined rules to identify archetypes, which subsequently map to career recommendations.

Inference Strategy & Rules Structure

Details the forward chaining execution cycle inside the CLIPS IDE. Describes user profile assertions, intermediate rule firing thresholds, and final priority output logic filtering utilizing salience weights.

What I Learned

• Expert Logic Coding: Learned to structure complex diagnostic knowledge bases using CLIPS constructs like deftemplate, defrule, and deffacts.
• Inference Tree Architecture: Developed a solid understanding of forward chaining logic where inputs trigger multi-stage intermediate facts (Archetypes) which eventually yield recommendations.
• Salience Filtering: Implemented rule prioritization and selection mechanics to sort recommendations and output only the top 3 matches to prevent information overload.
• Validation & Bounds checking: Programmed user-defined input validation loops in CLIPS (deffunctions) to check numerical ranges and string constraints securely.