A Novel Hybrid AI Framework for Career Path Recommendation Integrating SBERT Semantic Matching and TabTransformer for Structured Data
Bibliographic record
Abstract
A third of students report uncertainty about their future career paths, often receiving generic guidance that ignores the richness of their profiles. We present CareerMind.AI, a hybrid recommendation system that fuses unstructured resume understanding with structured academic and preference data. The system ingests either a resume or manual inputs (skills, interests, degree, age, CGPA) and produces career suggestions, missing-skill insights, and an interactive guidance experience. Unstructured text is embedded with Sentence-BERT (SBERT) and matched using cosine similarity; structured fields are modeled using a deep tabular model (TabTransformer/Category-Embedding) trained over TF-IDF features and scaled numerics. On a corpus of 5k+ student profiles, the resume-only engine reaches a 73% simulated match accuracy, while the structured model attains 95.9% accuracy after hyperparameter tuning. The approach runs locally without third-party inference dependencies for core recommendations, and is deployed as a Streamlit application with optional chatbot assistance. We release implementation details and assets to support reproduction and extension.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".