Interested in STEM & exploring the unseen.

I am an aspiring AI & Data Scientist with interests in backend development and HRD — building ERP solutions and learning continuously. I enjoy turning messy data into crisp decisions and building systems that help people work smarter.

AI / ML
Data Science
Backend (FastAPI, Flask)
ERP & HRD
Python
Databases
See Projects Download Resume

About me

Personalization / background (editable)

Interested in STEM, becoming an AI and Data Scientist, backend, HRD (working with ERP solution, developing it through continuous learning). Exploring the worlds unseen area.

I'm graduated in Human Resource Management. (BBA-HRM)

I build small tools, prototypes, and dashboards. I prefer pragmatic, well-tested code and clear visualizations.

Technical

  • Python (pandas, scikit-learn, numpy)
  • FastAPI / Flask
  • SQL / PostgreSQL
  • Machine learning pipelines

Data & Tools

  • Jupyter / Colab
  • Docker
  • Git / GitHub
  • Tableau / Matplotlib / Folium

Soft / HRD

  • Requirement gathering for ERP
  • Training & documentation
  • Process mapping
  • Continuous learning mindset

Projects

Customer Churn Prediction

Python · scikit-learn · pandas

A small classification pipeline predicting churn with feature engineering, cross-validation and a simple dashboard.

# sample (click to expand) import pandas as pd from sklearn.ensemble import RandomForestClassifier # load, preprocess, train

ERP — HR Module Prototype

Flask · SQLite · HTML

Prototype HR module: employee records, leave management, and simple reporting for HR admins.

# Flask example from flask import Flask, request, jsonify app = Flask(__name__) @app.route('/api/employees') def list_employees(): return jsonify([])

Backend API (FastAPI)

FastAPI · PostgreSQL · Docker

A demo REST API for employee & payroll endpoints with JWT auth and tests.

# FastAPI snippet from fastapi import FastAPI app = FastAPI() @app.get('/health') def health(): return {'status':'ok'}

Chittagong Map Visualization

GeoPandas · Folium · Matplotlib

Interactive map showing points of interest and simple choropleth by ward.

# Folium quickstart import folium m = folium.Map(location=[22.3569,91.7832], zoom_start=12)

Project showcase — expanded with code

Each project has a short description, tech stack, and a small runnable code snippet for rapid review.

Customer Churn Prediction — condensed notebook 
# Data science mini-notebook
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import classification_report

df = pd.read_csv('data/churn.csv')
X = df.drop('churn', axis=1)
y = df['churn']
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.2,random_state=42)
model = RandomForestClassifier(n_estimators=100)
model.fit(X_train, y_train)
print(classification_report(y_test, model.predict(X_test)))

Contact

Interested in collaborations or internships? Let's talk.

Email: n4zt.global@gmail.com

Email me