Freelancers using KerasFreelancers using Keras
ProjectsPeople
Istiak Ahmed Khan's avatar
Istiak Ahmed Khan
Dhaka, Bangladesh
Power BI Data Analyst + ML AI Automation Expert
5.0
Rating
107
Followers
Power BI Data Analyst + ML AI Automation Expert
Cover image for End-to-End Machine Learning Pipeline for
End-to-End Machine Learning Pipeline for Telecom Customer Churn 1. The Business Problem Customer churn is a major challenge for telecommunications companies, driven by competition, service issues, and changing consumer preferences. This project was designed to transition the company from reactive support to proactive retention using data-driven strategies such as customer segmentation, personalized offers, and loyalty programs,. 2. Data Exploration & Insights (EDA) I performed a comprehensive descriptive analysis on a database of 7,043 customers with 21 distinct variables,. Key findings included: Contractual Risk: Customers on month-to-month contracts showed significantly higher churn compared to those on one- or two-year commitments,. Service Preference: While Fiber Optic plans were the most popular, they also represented a critical segment for monitoring due to their higher price points,. Financial Indicators: Churned customers had a higher average monthly charge of $74.44, compared to $61.27 for retained customers. Payment Behavior: The "Electronic Check" payment method was most strongly associated with service cancellation,. 3. Engineering & Preprocessing Pipeline To prepare the data for high-performance modeling, I implemented a rigorous preprocessing workflow: Data Cleaning: Removed irrelevant identifiers like customerID and addressed potential data quality issues. The dataset was verified to have zero missing or NaN values,. Feature Engineering: Applied Label Encoding to transform categorical text variables into a numerical format suitable for machine learning algorithms,. Data Splitting: Adopted a standard 80/20 train-test split to ensure the model could generalize effectively to unseen data,. 4. Model Development & Benchmarking I developed and benchmarked eight distinct machine learning algorithms to identify the most effective solution for this specific application: Linear & Probabilistic: Logistic Regression, Naive Bayes. Tree-Based: Decision Tree, Random Forest. Boosting Frameworks: AdaBoost, Gradient Boosting, XGBoost, and LightGBM,. 5. Performance Evaluation & Results Models were evaluated using ROC curves, confusion matrices, and detailed classification reports,. Winner: Logistic Regression achieved the highest accuracy at 81.83%,. Secondary Performers: Gradient Boosting (81.05%) and AdaBoost (80.98%) also showed strong predictive power. 6. Technical Conclusion This data-driven approach proves that proactive churn prediction is essential for business sustainability. By identifying that customers prioritize high-speed fiber optic services but are sensitive to pricing and contract terms, the company can now optimize its pricing and retention strategies to maximize user satisfaction and revenue.
4
715
Cover image for The E-Commerce Orders Dashboard provides
The E-Commerce Orders Dashboard provides a comprehensive overview of order performance, revenue trends, and customer purchasing behavior. Designed for online businesses, this dashboard transforms transactional order data into actionable insights that support growth, operational efficiency, and strategic decision-making.
2
11
1.3K
Cover image for Email Marketing Analytics Dashboard –
Email Marketing Analytics Dashboard – UI/UX Design Struggling to track campaign performance across multiple channels? This dashboard is designed to give you a complete, real-time view of your marketing efforts in one clean and intuitive interface. A powerful, easy-to-use dashboard that helps you monitor email, SMS, social media, and push campaigns without the confusion of scattered data. Every key metric is presented clearly so you can make faster, smarter decisions. Key Capabilities: Track open rates, click rates, conversions, and revenue in real time, Compare performance across multiple marketing channels, Identify your top-performing campaigns instantly, Understand audience engagement with clear visual breakdowns, Spot trends and optimize campaigns quickly. Most businesses run campaigns but struggle to understand what’s actually working. This dashboard eliminates guesswork by turning your data into clear, actionable insights — helping you improve ROI and scale winning strategies. Perfect For: Digital marketers, E-commerce brands, Agencies managing multiple campaigns, Startups looking to optimize growth. If you want a high-converting, professional dashboard that not only looks great but drives real business decisions — I can help you build it.
8
18
956
Cover image for Comprehensive Financial Performance Dashboard in Power BI
The Financial Performance Dashboard provides a comprehensive overview of an organization’s financial health by tracking revenue, expenses, profitability, and key financial indicators. Built using Power BI, this dashboard enables finance teams and decision-makers to monitor performance, identify trends, and make data-driven strategic decisions.
6
1K
Keras(1)
Anurag Nagare's avatar
Anurag Nagare
Mumbai, India
I’m an AI & Machine Learning engineer with expertise in deve
I’m an AI & Machine Learning engineer with expertise in deve
Cover image for I recently built an AI-powered Mental Health Screening & Cli...
I recently built an AI-powered Mental Health Screening & Clinical Support System designed to assist both individuals and healthcare professionals in early detection and intervention. The system combines patient-reported questionnaires (PHQ-9 & GAD-7) with advanced NLP-based text analysis to assess depression, anxiety, and crisis risk levels. Based on the results, it generates personalized recommendations, safety plans, and professional referral letters, ensuring timely access to the right resources. This solution addresses a critical real-world problem: the growing gap in mental health care access. Many individuals experience symptoms but delay seeking professional help. Ultimately, it helps reduce the risk of untreated mental health crises and improves overall care outcomes.
0
77
Cover image for Everyone's building AR filters and
Everyone's building AR filters and calling it "computer vision magic." Almost nobody's asking what's actually happening underneath — that most of these effects are just clever masking, not detection. Here's proof. I built an invisibility cloak that runs entirely in the browser, no green screen, no chroma key, no model training. https://github.com/AnuragNagare/Ghost-frame
4
2
210
Cover image for What your attention heatmap isn't
What your attention heatmap isn't telling you Everyone's staring at attention heatmaps and calling it "interpretability." Almost nobody's asking whether a single attention map actually tells you what the model used to make its decision. It doesn't. Not on its own. A raw attention map from layer 8 shows you what layer 8 attended to. It says nothing about how that signal got mixed, diluted, or overwritten by every layer before and after it. Attention rollout fixes this — and I built a walkthrough to show why it matters. Here's what makes it more than a "pretty heatmap" demo: Instead of visualizing one layer's attention, I traced how information actually flows through the full transformer stack. → Every layer's attention matrix is extracted, per head, per token → Multi-head attention is averaged, then combined with the residual connection (identity + attention) — this is the step most tutorials skip, and it's the one that actually matters → The combined matrices are matrix-multiplied layer by layer, rolling attention forward from input to output → The result: a single map showing genuine token-to-token influence across the entire network, not just one layer's snapshot The overlay shows you everything: → Per-layer attention vs. rolled-out attention, side by side → Token importance scores overlaid directly on the input text → A comparison view: which tokens raw attention says "matter" vs. which ones rollout says actually matter → Head-level breakdown so you can see which heads specialize vs. which are noise No black box. No "trust me, the model looked here." Just linear algebra, applied honestly across every layer instead of cherry-picking one. Built with PyTorch + HuggingFace Transformers + Matplotlib. Runs on any pretrained transformer, fully offline. ⚠️ Important: attention rollout is an approximation, not ground truth. It assumes attention is the primary information pathway, which ignores MLP layers and can still mislead for very deep models. Treat it as a debugging lens, not proof of causality.
0
69
Cover image for Everyone's racing to add biometrics
Everyone's racing to add biometrics to logins. Almost nobody's asking what happens when you can't — or shouldn't — touch the sensor. Shared kiosks, clinical settings, accessibility needs, hygiene-sensitive environments. Fingerprint readers and face unlock assume contact or a stored faceprint. Sometimes you want authentication that touches nothing and stores no biometric image of you at all. So I built GestureAuth — a contactless authentication system where your "password" is a sequence of hand gestures performed in front of a standard webcam.
1
62
Keras(1)
Manideep racharla's avatar
Manideep racharla
Overland, USA
Data Analyst turning Data insights into business impact.
5.0
Rating
2
Followers
Data Analyst turning Data insights into business impact.
Cover image for Optimizing Home Delivery in Small Grocery Stores
Optimizing Home Delivery in Small Grocery Stores
0
6
Cover image for Parking Lot Utilization Analysis Dashboard
Parking Lot Utilization Analysis Dashboard
2
38
Cover image for Predictive Analysis of Airline Delays Using Machine Learning
Predictive Analysis of Airline Delays Using Machine Learning
0
6
Cover image for Stock Price and Trading Indicators Analysis
Stock Price and Trading Indicators Analysis
0
3
Keras(1)
Dylan Guidry's avatar
Dylan Guidry
Canada
Senior Software Engineer | 10+ Yrs Across Industries
8
Followers
Senior Software Engineer | 10+ Yrs Across Industries
Cover image for AI-Powered COVID-19 Detection via Chest X-Rays
AI-Powered COVID-19 Detection via Chest X-Rays
1
7
Cover image for AI-Powered Produce Inspection System
AI-Powered Produce Inspection System
1
5
Cover image for Forge SoftwareHub - Applied AI Development for Web, Mobile & Bl…
Forge SoftwareHub - Applied AI Development for Web, Mobile & Bl…
1
7
Cover image for AI-Powered Deposition Summaries for Legal Cases
AI-Powered Deposition Summaries for Legal Cases
1
26
Keras(2)
karthikeya Yelamanchili's avatar
karthikeya Yelamanchili
Hyderabad, India
Builds AI And help business to grow 10x with quality
New to Contra
Builds AI And help business to grow 10x with quality
Cover image for Facial Emotion Detection with Deep Learning
Facial Emotion Detection with Deep Learning
1
0
Cover image for Development of Appointment Scheduler Web App
Development of Appointment Scheduler Web App
0
0
Cover image for Machine Learning Stock Price Prediction for Google
Machine Learning Stock Price Prediction for Google
0
0
Cover image for OCR-Based Product Information Scanner
OCR-Based Product Information Scanner
0
0
Keras(1)
MoonTech OneSixEight's avatar
MoonTech OneSixEight
Almelo, Netherlands
Tech Renaissance Leader: AI, FinTech, Web
Tech Renaissance Leader: AI, FinTech, Web
Cover image for Multi-MT5 Integrated, AI-Infused Financial Sentiment Engine
Multi-MT5 Integrated, AI-Infused Financial Sentiment Engine
0
20
Cover image for QuantumTrade ML Suite
QuantumTrade ML Suite
0
47
Cover image for AI MCQ | FIFA
AI MCQ | FIFA
0
11
Placeholder project card media
View more →
Keras(1)