ANJALI
PAL • Data Scientist • Statistician• Data Analyst

About Me Projects Blog

About Me

Professional Me

Data is 'The Gauntlet' that has the Infinity Stones for revolutionizing the world.

Hi, I'm Anjali Pal — a passionate Data Scientist with a strong foundation in statistics and a fascination for how data can revolutionize the world.

My journey into data science began in 2018 during my undergraduate studies in Statistics at Lady Shri Ram College, University of Delhi. I landed an internship at a travel-based AI startup, and during the interview, the founder told me he was impressed by my genuine curiosity in AI — especially given I was only in my second year. That conversation gave me clarity: I wanted to build a career where I could combine curiosity, coding, and problem-solving — and data science was the perfect fit.

After completing my BSc, I pursued an MSc in Data Science and Machine Learning at University College London (UCL). As part of my thesis, I collaborated with Ocado Technology, where I worked with deep learning models — including transformers — for demand forecasting across thousands of products, using millions of rows of real transactional data.

Since graduating, I’ve joined Hastings Direct as a Data Scientist, where I develop and deploy scalable ML solutions for fraud detection, pricing optimization, and customer insights using tools like Azure ML, Snowflake, Python, and Power BI. My role also includes working with big data pipelines, running A/B tests, and translating complex models into actionable business outcomes.

But beyond code and data, I’m also someone who:
- Loves fiction – especially thrillers and mysteries like the Robert Langdon series (Dan Brown), The Millennium Trilogy (Stieg Larsson), and The Bancroft Strategy (Robert Ludlum)
- Dreams of traveling to every country and trying their local cuisine
- Enjoys archery, with shooting next on my list
- Believes coding is magical – it’s how we teach machines to learn from data, and that still fascinates me every day

I’m an optimistic, forward-thinking person who lives by one of my favorite quotes:

"Life is like riding a bicycle. To keep your balance, you must keep moving." – Albert Einstein

Languages and Tools

c cplusplus python scikit_learn tensorflow IBM SPSS Google Data Studio
R Tableau Pandas Numpy Keras Matplotlib AML Snowflake Databricks PowerBI

Data Science Projects

Recommendation Engine

Hybrid Movie Recommendation Engine

   

This project aimed at developing a hybrid recommendation engine by using MovieLens dataset which can recommend movies based on content and collaborative filtering to the user based on his prior choice.

Check it out!
Mobile Robot : MoBot

Mobile Robot : MoBot

 

During a group project at IIT Kanpur, along with my team, I created this obstacle avoiding mobile survellaince robot using Linear Separatrix approach. This robot uses ultrasonic distance sensor module and machine laerning algorithm to work.

Check it out!
ML algos

Implementation of common ML Algorithms

   

This repository on GitHub contains the algorithms which I've implemented on various datasets. It includes both supervised and unsupervised algorithms.

Check it out!
Infographic

Data Visualization using Infographics

 

Are you a basketball fan? If yes, I'm sure you must've wondered who is better LeBron James or Michael Jordan. I've used exploratory data analysis and joined the data to see patterns.

Check it out!

Open Source Contributions

OneStep ML

Content Enhancement for Linear Regression at OneStep ML

OneStepML is a community-led, open-sourced, e-learning platform for Machine Learning and Data Science, developed at elecTRON. I am currently working on the enhancement of their Linear Regression algorithm under Machine Learning- Easy Track.

Check it out!
BLM

Data collection for Fortune 100 companies at DiversityCorp

DiversityCorp is an open source project committed to holding companies accountable. The project involved collecting data on what the company statements during black lives matter campaign versus what changes had they actually done to ensure that no such discrimination further takes place in their firms. I contributed by collecting comprehensive secondary data for 20 companies.

Check it out!
spanish

Machine learning algorithms for Spanish speaking populations

This project aimed at collecting notebooks with different data science and data exploration techniques which later converted into Spanish for students. I contributed by adding well-explained algorithms for K means clustering and Decision Trees.

Check it out!

Research Projects

Transformers

Text Summarisation using BERT and T5 on the Wikihow Dataset

Transformer models have grown in popularity in recent years. This is primarily due to the self-attention mechanism in their architecture and the ability for parallelization. This paper proposes experiments for text summarisation using the WikiHow dataset. We use two models in a contest to outperform each other- BERT-large (extractive text summarizer) and T5-small (abstractive text summarizer).

Check it out!
Timeseries

Time Series Analysis on Petroleum : The Fuel of Life

The project aimed to study the change in the prices over 33 years and forecast the prices for the coming years to study its implications.

Check it out!
Flipkart Amazon

Comparative study between Amazon and Flipkart

The main objective of this project is to analyze the various factors that affect a consumer’s choice on Amazon or Flipkart and to perform a comparative study and find out which one of them both is leading the Indian e-commerce market and the reasons for its success.

Check it out!

Blog

GDS

Dynamic Dashboards using Google Data Studio

Whenever we come across any datasets, we see thousands or even millions of rows of data that do not make any sense. But this data has a lot of hidden potentials that can be discovered by a specialist. These specialists generally use data visualization tools to analyze data and draw insights from the data. Excel, Tableau, Google Data Studio, PowerBI, Python libraries like Seaborn, Matplotlib, etc. are some commonly used tools.

Check it out!
Scikit

Decision Trees using Sklearn

With decision trees, AI can make well-thought decisions without any human interference. Decision trees is a supervised learning algorithm which is used to solve both regression and classification problems. It is a predictive modelling approach that gives a graphical representation of decisions and every possible outcome because of that decision.

Check it out!
Master Python for Science in 30 Days

Master Python for Data Science in
30 Days

“Information is the oil of the 21st century, and analytics is the combustion engine.” — Peter Sondergaard, Gartner.
Ever wondered why you see advertisements on Youtube or Facebook or Google sites related to your current searches?
Don’t you think these ads make you buy luxury products more instead of necessary ones?

Check it out!
Want to read more of my articles?
Click here