Sabir Pulikkal
Pulikkal H,
Kudallur PO, Palakkad , Kerala
Pin: 679554
Mob: -
Email:-LinkedIn : www.linkedin.com/in/sabirp/
SUMMARY
To work with a progressive organization where I can contribute my technical skills and utilize my knowledge of Python, SQL,
Machine Learning, and Statistical analysis to solve Business challenges this would help us grow mutually and my
communication skills would help me to be collaborative and working together well as a team player so as to enhance my own
productivity at the same time achieving the organizational objectives with the attribute of time, quality and discipline.
EDUCATION/TRAINING
-
BANGALORE, India
IMARTICUS LEARNING
● Post graduate program in Data Analytics-
-
KERALA, India
MES COLLEGE OF ENGINEERING
●
Bachelor in Engineering (Applied Electronics and Instrumentation)– 65%
DR.NKMM MES CENTRAL SCHOOL
KERALA, India
● CLASS 12TH, CBSE (PCM)– 70%-
KERALA, India
DELHI INTERNATIONAL SCHOOL
● CLASS 10th, CBSE– 90%
SKILLS
1.
Data Analysis/Modeling
2.
3.
Data Visualization
Analytics/Data Tools & Language
4.
Other Languages and Technologies/Tools
ADEPT
Linear Regression, Logistics
Regression, Decision Tree, Random
Forest, KNN, SVM, Naive Bayes,
XGboost, Ada boost, K-means, NLP,
Statistics
Tableau
Python, Advanced Excel, MySQL,
Jupyter Notebook
HTML, CSS, VS Code, Git
EXPOSURE
Extra trees classifier, voting
classifier, PCA
Power-bi
R, SAS, Hadoop Ecosystem,
Spark, Databricks, Talend, SQL
Server.
Javascript, Django Framework,
Docker, AWS.
WORK EXPERIENCE
2018 - 2019 INDUSTRIAL AUTOMATION TRAINEE
KERALA
Eallisto Pvt Ltd
Description:
Worked as an Industrial Automation Engineer while mainly involving in the software aspects of PLC's , SCADA,
HMI and all other related hardware and technologies.
SKILLS
Good understanding of Business Analyst responsibilities, functions and all standard industry practices.
Strong multitasking skills along with time management.
Strong ability to learn new technologies with minimal guidance and time period.
Strong programming aptitude with ability to contribute in cross functional teams.
PROJECTS:
2019
Credit Risk Analysis
Tools used: Python
Activities
2020
Aim was to predict whether a loan will be default or not and whether the investors should lend the money to the
customers or not.
The Key highlight includes understanding of the data, data extraction and cleaning, features extraction, cross
validation, model fitting using Logistic Regression, Decision tree, Random forest, KNN.
Feature Engineering (Reducing Dimensions).
Grid-search to find the optimal hyper parameters of a model which assesses the risk based on business requirement.
AIR Quality Index Prediction
Tools used: Python (VS Code, Jupyter, Heroku )
Activities
●
●
●
●
●
●
2020
Breast Cancer Data
2020
Data collection by web scraping from tutiempo.net.
Extracting the table (consisting various features) from html using beautifulSoup for different years and month.
Combining all the data of different years and months to get the final data for analysis and prediction.
Data transformation.
Data modeling and Hyperparameter tuning for various ML algorithm to predict the air quality index.
Model deployment in real world using Heroku.
The goal is to classify whether the breast cancer isbenign or malignant.
This analysis aims to observe which features are most helpful in predicting malignant or benign cancer and to see
general trends that may aid us in model selection andhyper parameter selection.
Fitting model: SVM, Logistic Regression, Decision Tree, Random Forest.
EMPLOYEE CHURN ANALYSIS
Tools used: Python
Activities
●
●
●
●
●
Descriptive analysis to present and organize the IBM data.
Data exploration to visually understand the what happened and why it happened.
Key challenge was to use domain knowledge to extract important features.
Engineering new features to extract more information.
Generate insights/conclusions and translate them into recommendations and strategies to reduce churnrate.
