Help & Supportcareers@gravityer.com
AI Engineer with less than a year in Machine Learning & Data Science
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Software Engineering graduate with hands-on experience in machine learning, data science, and full-stack web development. Built 14+ ML projects on Kaggle covering recommender systems, NLP, clustering, classification, and regression on real-world datasets with up to 10,000+ records. Skilled in building end-to-end pipelines from data cleaning and feature engineering through model training, evaluation, and deployment. Seeking a Master's degree in AI / Data Science to deepen expertise in intelligent systems and advanced machine learning.
The Islamia University of Bahawalpur
BS Software Engineering · Software Engineering
November 1, 2021 – June 1, 2025
Book Recommendation System (Final Year Project)
June 1, 2024 – June 1, 2025
Built a full-stack web app that recommends books based on similar reader preferences using collaborative filtering. Designed a homepage displaying the top 50 popular books with title, author, rating, and cover images. Added a real-time search feature where users type a book name and instantly get similar suggestions. Cleaned and preprocessed a dataset of books, users, and ratings by removing missing values and duplicates. Started with a popularity-based model (minimum 250 ratings filter) before moving to collaborative filtering for better personalization. Trained the recommendation model on the processed dataset, achieving approximately 97% accuracy. Deployed the complete application online as a live web service using Flask.
AI Tool Recommender System
August 1, 2023 – May 1, 2024
Built a dual recommender system on a dataset of 10,000+ real AI tools that takes natural language queries and returns the most relevant tools. Implemented two approaches side by side: TF-IDF with Cosine Similarity for fast keyword matching and Sentence Transformers (all-MiniLM-L6-v2) for deeper semantic understanding. Engineered features like Context_Window_K, Has_API, and combined_text fields to improve NLP matching quality. Added user filters for Pricing Model, Primary Domain, and API Availability to refine recommendations. Achieved 99.70% accuracy with Logistic Regression and 99.90% with Random Forest on domain classification. Cached Sentence Transformer embeddings after first run to make subsequent searches instant.
Customer360: Segmentation, Churn & CLV Prediction
January 1, 2023 – July 1, 2023
Built an end-to-end customer analytics pipeline covering EDA, segmentation, churn prediction, and lifetime value estimation. Created RFM (Recency, Frequency, Monetary) features to describe customer behavior for better model inputs. Applied K-Means clustering with Elbow Method and 3D interactive Plotly scatterplots for meaningful customer grouping. Trained Logistic Regression for churn prediction (classification) and Random Forest Regressor for CLV prediction (regression). Included train vs test evaluation metrics to detect overfitting, making results production-ready.
LinguisticTimePredictor
November 1, 2022 – January 1, 2023
Deep learning regression model for predicting time-related linguistic features from text.
Player Market Value Prediction
September 1, 2022 – November 1, 2022
Regression model predicting football player market values from performance stats.
Football Match Outcome Prediction
September 1, 2022 – January 1, 2023
Built a model that predicts whether the home team will win, lose, or draw based on football match statistics. Performed data cleaning (removed nulls, handled missing referees) and engineered features like goal difference, total goals, and season extraction. Compared Logistic Regression, Random Forest, and XGBoost with automatic model selection for the best-performing algorithm. Achieved approximately 99% accuracy with evaluation via classification reports and confusion matrices.
GDP Growth Modeling
July 1, 2022 – September 1, 2022
Compared Logistic Regression, Random Forest, and XGBoost for economic growth prediction.
Car Value Depreciation Model
May 1, 2022 – September 1, 2022
Built a model predicting how much a car's price decreases over time based on year, fuel type, kilometers driven, and condition. Compared three models: Linear Regression (R² ≈ 95%), Decision Tree (R² ≈ 99.5%), and Random Forest (R² ≈ 99.8%). Selected Random Forest Regressor as the final model for best accuracy and lowest error. Performed cross-validation to confirm model stability, consistently showing >99% R² score across folds.
DataCamp Learning Path Recommender
May 1, 2022 – July 1, 2022
Content-based recommender system with 80% accuracy for personalized learning paths.
LuxuryDrive AI: BMW Sales Predictor
March 1, 2022 – May 1, 2022
Sales prediction model achieving 90% accuracy on BMW vehicle data.
Student Learning Profile Clustering
January 1, 2022 – May 1, 2022
Analyzed a student academic performance dataset to identify hidden patterns using unsupervised learning. Applied K-Means clustering to group students into meaningful categories based on study behavior and past performance. Performed data preprocessing, feature selection, and cluster validation to ensure robust groupings.
Stress Risk Profiling
January 1, 2022 – March 1, 2022
Clustering model to categorize individuals into stress risk profiles based on health indicators.
Award-Winning Disney Titles Prediction
November 1, 2021 – March 1, 2022
Built a model predicting whether a Disney title is award-winning using metadata like genre, runtime, IMDb ratings, language, and release year. Engineered new predictive features from runtime, rating, and genre data to improve model performance. Trained ensemble models (Random Forest and XGBoost), achieving 82% overall accuracy and 94% recall. Optimized for recall to minimize missed predictions of award-winning content.
Cultural Fit Analysis
The candidate's extensive portfolio of personal projects, including several Kaggle-style challenges, indicates a strong passion for AI/ML and a self-starter mentality. This aligns well with a culture that values initiative and continuous learning. The diversity of projects (recommendation systems, NLP, customer analytics, prediction models) shows a broad interest in applying AI to different domains. However, the lack of team-based projects or professional experience makes it difficult to assess collaboration and adaptability in a corporate environment.
Soft Skills & Operational Fit
The candidate demonstrates a proactive and self-driven attitude through a large number of personal and academic projects. The detailed descriptions indicate an ability to articulate technical processes and outcomes. However, without direct work experience or psychometric test results, it's difficult to assess stress handling, team collaboration, or broader operational fit.