Md Saiful Islam
Open to work1 years experienceData Analyst
Data Analyst solving industry problems using predictive modelling and real-time analytics.
Standing Rank
Rank Not Available
Developer Badges
Skills & Technologies
28 skillsGitHub Activity Evidence
GitHub Footprint Not Connected
Recruiters value verified code contributions. Linking a GitHub account displays live heatmaps, active contribution metrics, repository languages, and push activity tags.
Work Experience
Data Analyst
Softme Limited
- Engineered Python and SQL models for 4,500+ assets, closing critical visibility gaps in property and ownership trends.
- Synthesised datasets to boost valuation accuracy by 17%, providing high-precision insights for real estate planning.
- Accelerated reporting by 24% via automation, delivering actionable intelligence to streamline land management.
Team Leader
SubWay
- Weekly Stock counting & placing order and Handling cash, credit, and debit card payments.
- Prepare food neatly, accurately in a timely way and collaborate with colleagues to achieve store goals.
- Opening and closing the following established procedures of Subway.
Fleet Operator
Ryde Technology
- Maximized daily scooter availability via strategic battery swapping, eliminating service disruptions to meet peak commuter demand.
- Optimized fleet distribution across key urban zones via demand-driven relocation, reducing vehicle idle time to capture maximum user traffic.
- Streamlined field logistics via efficient service vehicle navigation, accelerating response times to achieve daily city-wide deployment targets.
Projects
House Price Prediction
- Manual real estate appraisals were inconsistent, slow, and caused market inefficiencies.
- Implemented a regression model using Polynomial Features and Linear Regression to estimate property values.
- Predicts sale prices within a 5% margin of error, streamlining valuation for agents, buyers, and sellers.
Cardiovascular Disease Early-Risk Predictor
- Doctors lacked a reliable method to identify high-risk patients early.
- Built a machine learning model using patient history and ensemble methods.
- 93% accurate, predicting risk 2 years earlier to enable early care.
Real-Time Customer Sentiment Analysis Pipeline
- Customer feedback was unmeasured in real time, causing missed opportunities.
- Built a scalable data pipeline with Spark, Kafka, and NLP.
- Processes 10k+ messages per hour at 94% accuracy for real-time brand tracking and agile decisions.
Automated Brain Tumour Detection System
- Manual MRI scan analysis is slow (days), delaying critical diagnosis.
- Developed a CNN using PyTorch to automate scan classification.
- Instant analysis, 97% accuracy — faster diagnosis and faster treatment.
BD Crime Map using Folium
- Lacked a geographic visualisation to identify and compare regional crime hotspots across Bangladesh.
- Built an interactive choropleth map plotting district-level crime data using Python's Folium library and GeoJSON.
- Provides clear visual identification of high-risk zones, enabling data-driven public awareness and policy focus.
ChatGPT Sentiment Analysis
- Had no measurable insight into user sentiment from interactions with the AI model, missing feedback opportunities.
- Built an NLP pipeline with text preprocessing and trained an LSTM model using TensorFlow to classify sentiment.
- Analyses user sentiment with 94% accuracy, delivering actionable reports on user experience and model reception.
Covid Vaccination Progress using Plotly
- Static reports failed to effectively communicate the dynamic progress of the global vaccine rollout.
- Created an interactive, animated dashboard using Plotly Express to visualise vaccination data across countries and time.
- Enabled real-time tracking and comparison of vaccination milestones, improving public information dissemination.
GPA Clustering using K-Means Algorithm
- Could not objectively segment students into distinct groups for targeted academic support based on behaviour.
- Applied the K-means algorithm and the Elbow Method to cluster students by study hours and GPA.
- Identified 4 distinct student clusters (e.g., "At-Risk"), enabling personalised academic advising and resource allocation.
Leaderboard Standings
Leaderboard Position Pending
Global test scores, peer standing percentiles, and algorithm leaderboard ranks are updated dynamically.
Assessment Highlights
Assessments Not Completed
Coding evaluations, system assessment results, and conceptual score badges will appear here after taking a test.
AI Collaboration Score
AI Collaboration Score Pending
Developer coding behavior, assistant cooperation, and AI pair-programming indicators are evaluated during live coding sessions.
Role Compatibility Profile
Role Compatibility Analysis Pending
Custom matching reports, candidate role compatibility percentiles, and core engineer strength profiles are processed once conceptual code screenings are complete.
Achievements
Measurable Outcomes
Achieved 12% higher accuracy and systems processing 10,000+ messages hourly.
About Details
Professional Bio
Data Analyst solving industry problems using predictive modelling and real-time analytics. Translates data into insights that improve decisions and boost efficiency. Achieves measurable outcomes such as 12% higher accuracy and systems processing 10,000+ messages hourly.
MSc in Data Analytics
University of Portsmouth ( - Present)
BSc in Computer Science and Engineering in Computer Science and Engineering
Daffodil International University (2017 - 2021)