I’m Malik Jamal Mehboob, a data scientist passionate about turning data into actionable insights. I enjoy building predictive models, performing statistical analyses, and communicating findings through clear visualizations. I take a hands-on approach to learning, have built scalable models and interactive dashboards, and thrive on solving real-world problems with data.…

Malik Jamal Mehboob

I’m Malik Jamal Mehboob, a data scientist passionate about turning data into actionable insights. I enjoy building predictive models, performing statistical analyses, and communicating findings through clear visualizations. I take a hands-on approach to learning, have built scalable models and interactive dashboards, and thrive on solving real-world problems with data.…

Available to hire

I’m Malik Jamal Mehboob, a data scientist passionate about turning data into actionable insights. I enjoy building predictive models, performing statistical analyses, and communicating findings through clear visualizations.

I take a hands-on approach to learning, have built scalable models and interactive dashboards, and thrive on solving real-world problems with data.

See more

Skills

Experience Level

Python
Expert
Data Science
Expert
TensorFlow
Expert
SQL
Expert
PyTorch
Expert
Keras
Expert
MySQL
Expert
PostgreSQL
Expert
Hadoop
Expert
Power BI
Expert
GitHub
Expert
Docker
Expert
Data Visualization
Expert
Tableau
Expert
AWS
Expert
Jira
Intermediate
Selenium
Intermediate
See more

Language

English
Advanced

Work Experience

Product Manager at Nexus Telecom
July 1, 2022 - Present
Led a team of 10 in Revenue Assurance and Fraud Detection, leveraging data-driven insights to optimize telecom network performance before live deployment. Spearheaded AI-driven performance testing for GSM (2G/3G/4G/LTE) using Head Spin Platform, enhancing OTT application reliability. Developed automated testing frameworks with Appium, Selenium, Jenkins, and Postman API, streamlining quality assurance for Jazz. Utilized SQL, PostgreSQL, and cloud analytics for telecom data processing, driving insights for international roaming and network optimization. Managed Linux/MAC-based CLI servers and implemented CI/CD pipelines, ensuring scalable and efficient telecom and data science workflows.
Customer Project Engineer at Nexus Telecom
June 1, 2022 - September 25, 2025
Analyzed and optimized call routes using SS7 trace analysis, leveraging data-driven insights to enhance telecom network efficiency. Provided real-time technical support, troubleshooting critical application issues and ensuring seamless customer operations. Collaborated with Level 2 & 3 engineers, using data insights to diagnose and rectify complex configuration issues. Integrated Salesforce analytics for tracking customer interactions and improving support response strategies. Conducted site surveys & live link cutovers, ensuring data-driven decision-making for network deployment and optimization.
Technical Support Engineer at Nexus Telecom
June 1, 2021 - September 25, 2025
Monitored applications and system interfaces, analyzing alarm data to ensure optimal network performance; configured routers, switches, and installed servers for seamless connectivity. Resolved 95% of software issues during implementation using data-driven debugging and performance analysis techniques. Deployed and tested End-User Probes (EUP) globally, analyzing Voice, SMS, and Data flows to generate insightful reports for network optimization. Provided real-time customer support for JAZZ, UFONE, and ZONG, leveraging data analytics to enhance troubleshooting and service quality.
Product Manager at Nexus Telecom
July 1, 2022 - Present
Led a team of 10 in Revenue Assurance and Fraud Detection, leveraging data-driven insights to optimize telecom network performance before live deployment. Spearheaded AI-driven performance testing for GSM/OTT reliability, developed automated testing frameworks (Appium, Selenium, Jenkins, Postman) for QA, and utilized SQL, PostgreSQL, and cloud analytics for roaming and network optimization. Managed Linux/Mac CLI servers and implemented CI/CD pipelines to streamline telecom and data science workflows.
Customer Project Engineer at Nexus Telecom
June 1, 2022 - September 25, 2025
Analyzed and optimized call routes using SS7 trace analysis; provided real-time technical support; collaborated with Level 2 & 3 engineers to diagnose and rectify complex configuration issues. Integrated Salesforce analytics for tracking customer interactions and conducted site surveys and live link cutovers to support network deployment and optimization.
Technical Support Engineer at Nexus Telecom
June 1, 2021 - September 25, 2025
Monitored applications and system interfaces; analyzed alarm data to ensure optimal network performance; configured routers and switches, installed servers, and resolved 95% of software issues during implementation using data-driven debugging. Deployed End-User Probes (EUP) globally to analyze Voice, SMS, and Data flows for network optimization and provided real-time support for Jazz, UFONE, and ZONG.
Operations Manager at Nexus Telecom
July 1, 2022 - Present
Led a team of 10 in Revenue Assurance and Fraud Detection, leveraging data-driven insights to optimize telecom network performance before live deployment. Spearheaded AI-driven performance testing for GSM (2G/3G/4G/LTE) using the HeadSpin Platform, enhancing OTT application reliability. Developed automated testing frameworks with Appium, Selenium, Jenkins, and Postman API, streamlining QA for Jazz. Utilized SQL, PostgreSQL, and cloud analytics for telecom data processing, driving insights for international roaming and network optimization. Managed Linux/Mac-based CLI servers and implemented CI/CD pipelines, ensuring scalable and efficient telecom and data science workflows.
Customer Project Engineer at Nexus Telecom
June 30, 2022 - September 25, 2025
Analyzed and optimized call routes using SS7 trace analysis, leveraging data-driven insights to enhance telecom network efficiency. Provided real-time technical support, troubleshooting critical application issues and ensuring seamless customer operations. Collaborated with Level 2 & 3 engineers, using data insights to diagnose and rectify complex configuration issues. Integrated Salesforce analytics for tracking customer interactions and improving support response strategies. Conducted site surveys & live link cutovers, ensuring data-driven decision-making for network deployment and optimization.
Technical Support Engineer at Nexus Telecom
June 30, 2021 - September 25, 2025
Monitored applications and system interfaces, analyzing alarm data to ensure optimal network performance; configured routers, switches, and installed servers for seamless connectivity. Resolved 95% of software issues during implementation using data-driven debugging and performance analysis techniques. Deployed and tested End-User Probes (EUP) globally, analyzing Voice, SMS, and Data flows to generate insightful reports for network optimization. Provided real-time customer support for Jazz, UFONE, and ZONG, leveraging data analytics to enhance troubleshooting and service quality.

Education

Masters in Data Science at Bahria University
January 1, 2024 - January 1, 2026
Bachelor of Computer Science at PMAS Arid Agriculture University
January 1, 2015 - January 1, 2019

Qualifications

Python for Data Science (IBM)
January 1, 2020 - September 25, 2025
Mobile App Development
January 1, 2018 - September 25, 2025
Foundations of Project Management
January 1, 2022 - September 25, 2025
Foundations Data, Data Everywhere
January 1, 2022 - September 25, 2025
Python for Data Science
January 11, 2030 - September 25, 2025
Deep Learning Fundamentals
January 11, 2030 - September 25, 2025

Industry Experience

Telecommunications, Software & Internet, Professional Services, Media & Entertainment, Education
    paper Loan Approval Prediction
    Loan Approval Prediction This repository contains a comprehensive Jupyter Notebook (Loan_Approval_Prediction_Description_.ipynb) focused on predicting loan approvals using various machine learning techniques. Overview This project follows a complete binary classification pipeline tailored for the loan approval domain. It includes: Exploratory Data Analysis (EDA): Understanding feature distributions, missing values, and correlations. Data Cleaning & Preprocessing: Handling missing data, encoding categorical features, and normalization. Modeling: Training and comparing models, including Logistic Regression, Decision Tree, and XGBoost. Imbalance Handling: Addressing class imbalance through upsampling or synthetic methods (e.g., SMOTE). Evaluation: Utilizing metrics like precision, recall, F1-score, ROC-AUC, and confusion matrices for balanced assessment. Bonus Comparisons: ROC curves, hyperparameter tuning, and feature importance analysis to identify model strengths and important predictors. Dataset The notebook uses the Loan Approval Prediction Dataset from Kaggle by architsharma01, which includes features like: Gender, Marital Status, Dependents, Education, Applicant Income, Co-applicant Income Loan Amount, Loan Term, Credit History, Property Area Target variable: Loan_Status (Approved = 1, Not Approved = 0) Ensure you've downloaded the dataset and uploaded it to the notebook environment—typically named loan_approval_prediction_dataset.csv. Step-by-Step Notebook Workflow Load the data into a Pandas DataFrame. Inspect data for missing values, data types, and target distribution. Visualize using bar plots, heatmaps, and histograms. Data cleaning: Fill missing values with median or mode. Encode categorical columns using LabelEncoder. Split data into train/test sets with stratification to preserve class distribution. Optionally apply SMOTE to mitigate class imbalance. Train and evaluate three models: Logistic Regression Decision Tree XGBoost Generate classification reports (precision, recall, F1-score) and confusion matrices. Compare models with summary bar charts of metrics. Plot ROC-AUC curves with AUC scores for each model. Analyze feature importance across models to understand key predictors. Visualization Highlights Class Distribution – Understand imbalance in Loan_Status. Correlation Heatmap – Reveal interactions between numeric features. Confusion Matrices– Visualize errors for each classifier. ROC Curves – Compare discrimination ability across models. Feature Importance – Evaluate which variables drive model decisions.…
    paper 🧠 Customer Segmentation using K-Means Clustering
    🧠 Customer Segmentation using K-Means Clustering This project applies K-Means Clustering, an unsupervised machine learning algorithm, to perform customer segmentation based on behavioral data. The objective is to identify distinct customer groups to help businesses tailor marketing strategies and improve customer retention. 📌 Objective To group customers into segments based on common traits such as age, income, and spending score using clustering techniques. This segmentation can help companies: Personalize marketing campaigns Identify high-value customers Design better product offerings 📊 Dataset The project uses a Mall Customer Dataset (or similar), which includes the following features: CustomerID Gender Age Annual Income (k$) Spending Score (1–100) 🚀 Project Workflow Data Preprocessing Handling missing values Feature selection Encoding categorical variables if required Exploratory Data Analysis (EDA) Distribution of age, gender, income, and spending score Pairplots and correlation analysis Visualizing customer patterns Feature Scaling Normalization using StandardScaler Optimal Cluster Selection Elbow Method to determine the ideal number of clusters Model Training KMeans clustering using scikit-learn Assigning cluster labels to each customer Cluster Visualization 2D/3D plots to visualize customer segments Colored cluster plots with income vs. spending behavior 🧠 Key Learnings How unsupervised learning works for pattern discovery Importance of feature scaling in distance-based models Using the Elbow Method for optimal cluster selection Gaining business insights from data patterns 📚 Libraries Used Python (Jupyter Notebook) Pandas & NumPy Matplotlib & Seaborn Scikit-learn 📈 Outputs Identified 3–5 meaningful customer segments Visualized spending vs. income for different clusters Gained actionable insights for customer-centric strategies…
    paper 🌲 Forest Cover Type Classification
    🌲 Forest Cover Type Classification This project predicts the forest cover type from cartographic variables such as elevation, slope, soil type, and wilderness area. It uses machine learning models to classify forest cover into one of seven types based on data from the UCI Covertype dataset. 📌 Overview Goal: Build an accurate model to classify forest cover type from environmental features. Dataset: UCI Covertype (~581k rows, 54 features, 7 cover types). Approach: Data preprocessing, EDA, model training, and explainability using SHAP. Best Model: XGBoost classifier with high accuracy. 📂 Dataset Source: UCI Machine Learning Repository - Covertype Dataset Target Variable: Cover_Type (values 1–7) Features: Elevation, Aspect, Slope, Horizontal/Vertical Distances, Soil Type, Wilderness Area, etc. 🛠️ Technologies Used Languages: Python Libraries: Data: pandas, numpy Visualization: matplotlib, seaborn Machine Learning: scikit-learn, xgboost Explainability: shap Utilities: joblib 🚀 Project Workflow Imports & Constants – Load libraries and set parameters. Data Loading – Download and read dataset into DataFrame. Data Inspection – Check structure, types, and missing values. Exploratory Data Analysis (EDA) – Visualize class distribution, correlations, and feature impacts. Preprocessing – Train-test split, scaling, and encoding. Model Training – Compare Logistic Regression, Random Forest, and XGBoost. Evaluation – Accuracy, Precision, Recall, F1-score. Explainability – SHAP analysis to understand feature importance. 📊 Results Best model: XGBoost Top features: Elevation, Soil Type, Horizontal Distance to Hydrology Key insight: Elevation and soil type have the strongest influence on forest cover classification.…
    paper Movie Recommendation System
    🎬 Movie Recommendation System This project implements a Movie Recommendation System using the MovieLens 100K dataset. It compares three popular recommendation approaches: User-Based Collaborative Filtering (User-CF) Item-Based Collaborative Filtering (Item-CF) Matrix Factorization (SVD) Finally, it evaluates models using Precision@K and visualizes performance with comparison graphs. 📂 Dataset Dataset: MovieLens 100K Contains 100,000 ratings from 943 users across 1,682 movies. Includes metadata such as movie titles, genres, and release dates. ⚙️ Features ✅ User-Based Collaborative Filtering ✅ Item-Based Collaborative Filtering ✅ Matrix Factorization with SVD ✅ Precision@K evaluation metric ✅ Performance visualization (bar plots) ✅ Easily extendable for other datasets 📊 Results (Sample Precision@5) Model Precision@5 User-CF 0.40 Item-CF 0.46 SVD 0.52 🔹 Results may vary depending on random users chosen for testing. 🚀 Installation & Setup Clone the Repository git clone https://www.twine.net/signin cd movie-recommendation-system Install Dependencies pip install -r requirements.txt requirements.txt: pandas numpy scikit-learn scipy matplotlib Run the Notebook Open Google Colab or Jupyter Notebook Upload the dataset into /content/ml-100k/ (Colab) or project folder (local) Run the steps in Movie_Recommendation_System.ipynb 🖥️ Project Workflow Load and preprocess MovieLens dataset Create User–Item Matrix Build User-CF model using cosine similarity Build Item-CF model using item similarity Apply Matrix Factorization (SVD) Evaluate recommendations with Precision@K Compare models with visual graphs 📌 Example Output User-Based Recommendations for User 1: Star Wars (1977) Raiders of the Lost Ark (1981) Empire Strikes Back, The (1980) Item-Based Recommendations for User 1: Return of the Jedi (1983) Jurassic Park (1993) SVD Recommendations for User 1: Fargo (1996) Contact (1997) 📈 Visualization Bar chart comparing average Precision@5 across models:…
    paper Telco_Churn_Prediction
    What is Customer Churn? Customer churn is defined as when customers or subscribers discontinue doing business with a firm or service. Customers in the telecom industry can choose from a variety of service providers and actively switch from one to the next. The telecommunications business has an annual churn rate of 15-25 percent in this highly competitive market. Individualized customer retention is tough because most firms have a large number of customers and can't afford to devote much time to each of them. The costs would be too great, outweighing the additional revenue. However, if a corporation could forecast which customers are likely to leave ahead of time, it could focus customer retention efforts only on these "high risk" clients. The ultimate goal is to expand its coverage area and retrieve more customers loyalty. The core to succeed in this market lies in the customer itself. Customer churn is a critical metric because it is much less expensive to retain existing customers than it is to acquire new customers. To detect early signs of potential churn, one must first develop a holistic view of the customers and their interactions across numerous channels.As a result, by addressing churn, these businesses may not only preserve their market position, but also grow and thrive. More customers they have in their network, the lower the cost of initiation and the larger the profit. As a result, the company's key focus for success is reducing client attrition and implementing effective retention strategy. Objectives: Finding the % of Churn Customers and customers that keep in with the active services. Analysing the data in terms of various features responsible for customer Churn Finding a most suited machine learning model for correct classification of Churn and non churn customers. Dataset: Telco Customer Churn The data set includes information about: Customers who left within the last month – the column is called Churn Services that each customer has signed up for – phone, multiple lines, internet, online security, online backup, device protection, tech support, and streaming TV and movies Customer account information – how long they’ve been a customer, contract, payment method, paperless billing, monthly charges, and total charges Demographic info about customers – gender, age range, and if they have partners and dependents Implementation: Libraries: sklearn, Matplotlib, pandas, seaborn, and NumPy…
    paper Heart_Disease_prediction
    The notebook appears to focus on a machine learning project related to cardiovascular disease prediction. Here’s a summary of its content: Introduction: The project begins with importing necessary libraries, such as pandas, numpy, and scikit-learn, along with the cardiovascular dataset. The goal is to build a predictive model to determine the likelihood of cardiovascular disease. Data Exploration and Preprocessing: Data exploration includes checking the dataset for missing values and basic descriptive statistics. Features are selected for modeling based on domain relevance, and the data is split into training and testing sets. Model Training: The project employs a logistic regression model, with accuracy as the key performance metric. The accuracy of the model was targeted at 95%, and model performance was evaluated accordingly. Results and Feature Importance: A bar plot was created to show feature importance, highlighting which factors contributed most to the prediction. Conclusion: The project successfully achieved its accuracy goal of 95%. Suggestions for further improvement include gathering more data, improving data quality, and trying other machine learning models to improve performance. This notebook offers a straightforward machine learning approach to cardiovascular disease prediction with logistic regression, focusing on data preprocessing, model training, and evaluation.…