Hey! I am

Saksham Arora

I'm a


Profile Image

About

About Me

As a Data Scientist with over five years of experience, I specialize in predictive modeling, machine learning, and data engineering. My role at Daimler Truck Financial Services within the Data Insights & Advanced Analytics team has provided deep expertise in credit risk forecasting, delinquencies, and financial analytics. Holding a Master’s degree in Data Analytics Engineering, I possess a strong foundation in both theoretical and applied data science, making me a strategic asset to any organization.

I bring a robust skill set that includes Generative AI, LLMs, Python-based Time-Series and Regression-based Machine Learning Algorithms, Advanced SQL, and Advanced Excel. My experience spans implementing end-to-end AI solutions, designing scalable ETL pipelines, and leveraging cloud technologies such as AWS, Azure, and GCP. I have successfully built and optimized high-impact machine learning models using tools like LightGBM, XGBoost, and Prophet, improving business decision-making with explainable AI and data-driven insights.

Beyond technical proficiency, I specialize in developing data and analytical services that challenge market standards while catering to both executive decision-makers and frontline analytical developers. My approach blends technical expertise with business acumen, ensuring that my solutions not only drive measurable impact but also align with strategic objectives. Passionate about cutting-edge AI and machine learning techniques, I continually push the boundaries of data science applications in financial and risk analytics.

  • Name: Saksham Arora
  • Date of birth: March 17, 1996
  • Address: Troy, Michigan
  • Zip code: 48084
  • Email: arorasaksham96@gmail.com
  • Phone: +1-703-980-3162
Social:

0 Projects Completed

Download CV

Resume

Resume

With a strong foundation in both my Undergraduate and Graduate Studies, I have meticulously honed my analytical skills and computational expertise, preparing me to tackle complex, data-driven challenges. My academic journey, coupled with hands-on experience in machine learning, predictive modeling, and data engineering, has equipped me with the ability to extract meaningful insights from vast datasets.

Throughout my career, I have worked extensively with Generative AI, LLMs, Python, Advanced SQL, and cloud-based data solutions, enabling me to develop scalable AI-driven solutions that enhance decision-making. From building time-series forecasting models for financial analytics to deploying end-to-end machine learning pipelines, I thrive at the intersection of innovation and data science.

Education

Logo
2018-2020

Masters of Science in Data Analytics Engineering

George Mason University

Volgenau School of Engineering, Fairfax, Virginia, USA. | GPA - 3.77

Logo
2014-2018

Bachelors of Science in Computer Science & Engineering

Amity University

Amity School of Engineering & Technology, Noida, India. | GPA - 3.8

Experience

Logo
January 2022 - Present

Data Scientist

Daimler Truck Financial Services
  • Led the development of a sophisticated Generative AI chatbot for Daimler Truck Financial Services, utilizing Azure OpenAI services for text summarization, named entity recognition, language translation, and question-and-answer functionalities.
  • Leveraged advanced NLP techniques to streamline operations, collaborating closely with stakeholders to ensure seamless integration and optimize performance.
  • Provided ongoing support and maintenance, refining the chatbot's capabilities to adapt to evolving business needs and technological advancements while maximizing efficiency through Azure OpenAI services.
  • Led the Data Insights and Advanced Analytics team in utilizing Python to develop time-series machine learning models, seamlessly integrating them into an Advanced Excel tool enabled with VBA. These models effectively identified the organization's business staffing and acquisition needs.
  • Spearheaded the formulation of a Collections Forecast model using advanced SQL and ML-based time series modeling techniques. This model enabled the Data Insights and Advanced Analytics team to accurately forecast delinquency numbers, measure credit losses, and analyze units sold, providing valuable insights for informed decision-making.
  • Designed and implemented robust anomaly detection and drift detection systems using advanced Python libraries and statistical techniques. These systems ensured data quality and reliability for business-critical models by effectively identifying outliers and detecting data drift, maintaining model accuracy and preventing performance degradation.
  • Developed and deployed high-performance predictive analytics solutions to enhance business forecasting, leveraging LightGBM, XGBoost, and Prophet to optimize model accuracy and interpretability.
  • Demonstrated expertise in Reporting, Data Modeling, Analysis, Tableau Visualization, and Data Warehousing within a professional industry environment. The insights generated were instrumental for business stakeholders, shaping key decisions in the credit paradigm for monthly, quarterly, and annual truck sales and repossessions.
  • Successfully constructed a prediction model using SQL for data collection, blending, and cleansing, with subsequent development in RStudio and a user-friendly UI built on R Shiny. The model, based on a blended version of the random forest algorithm, accurately predicted the fair market value of trucks at the end of a lease term, achieving an accuracy increase of over 75%, surpassing the threshold values of ±3%.
Logo
March 2021 - December 2021

Data Scientist

Mercedes Benz Financial Services
  • Spearheaded the Data Science team, leveraging Data Analytics resources including Python, Tableau, and machine learning models to predict and analyze the impact of macroeconomic factors on the company's revenue generation strategies. Additionally, developed accurate forecasts for various key performance indicators (KPIs) to anticipate potential losses.
  • Led the design and implementation of a robust prediction lifecycle and workflow, integrating machine learning tools, databases, and advanced SQL for iterative Model Evaluation (ME) activities, resulting in efficient and effective analysis.
  • Successfully automated the company's manual legacy workflow, enhancing it with additional features that significantly improved accuracy by more than ±5 and expedited output generation by an impressive 85%.
Logo
September 2019 - February 2021

Data Analyst

George Mason University
  • Idioms Analytics Project Led the development of an analytical platform leveraging Python, Amazon Web Services, and Tableau to analyze the quality of written media based on idioms from an Oxford dictionary dataset.
  • Voting Fraud Analysis Project Executed a comprehensive analysis of voting trends across various states in the USA, employing Python and web scraping techniques to detect and uncover instances of voting fraud, ultimately identifying the individuals involved in the fraudulent activities.
Logo
August 2017 - August 2018

Data Analyst

Auto Pearl (India)
  • Responsible for the complete ETL (Extract, Transform & Load) process.
  • Implemented the importing and exporting data using Flume and Kafka.
  • Created topic for accepting data related to online purchases.
  • Did the cleaning and structuring of data by using Python and R.
  • Responsible for implementing partitioning and bucketing in hive.
  • Developed and maintained the architecture of Redshift and EMR Clusters.
  • Handled the real time data by using Spark, which was installed on AWS EMR, with the Scala language.
  • Scheduled jobs for loading data into HDFS, by using Oozie.
  • Created dashboards and reports by using Power BI, for the sponsors.
Logo
May 2017 - July 2017

Big Data Intern

Webtek Labs (India)
  • Developed a Stock Market Analysis Project.
  • Performed web scraping, in order to calculate profits.
  • Converted unstructured data to structured data, to keep a track of the sales of the company.
Logo
September 2016 - October 2016

Student Ambassador

Nearbuy (Groupon)
  • Analysis of data using the R language.

Skills

Python

90%
95%
Last week
100%
Last month

R & R Studio

80%
84%
Last week
60%
Last month

Tableau

57%
28%
Last week
59%
Last month

Prompt Engineering

60%

Python

85%

Advanced Excel

45%

R & R Studio

50%

Tableau

95%

MySQL | PostgreSQL

80%

Frameworks | Tools

AWS Services

EC2, S3, CloudFront, Route53, Data Lakes, CloudWatch, DyanmoDB, EMR, Redshift, Data Warehouse, Lambda, SSL

Frameworks

Streamlit | Django | Flask

Visualization Tools

Taleau | Power BI

Statistical Tools

SAAS


Proficiency

Proficiency

As seasoned Data Scientist with over five years of industry experience, I bring advanced expertise in data analysis, predictive modeling, and artificial intelligence. Leveraging cutting-edge AI technologies and machine learning frameworks, I drive data-driven insights, optimize decision-making, and enhance business outcomes.

Data Analysis & ML Modeling

Data Analysis using Python and R.

Data Visualization

Visualization of data using Python, R and Tableau.

Prompt Engineering and Artificial Intelligence

In my recent professional endeavors, I have cultivated a specialized interest in Prompt Engineering and Artificial Intelligence. These are the focus areas I rigorously engage with during my independent research time.

Projects

Projects

Throughout my undergraduate and graduate studies, I led multiple high-impact projects that deepened my expertise in data science, machine learning, and AI, bridging the gap between academic research and real-world applications.

Idiom Trend Calculator and Analyzer

Analyzes the quality of written media in the books and articles that have been published. Calculates the trends of idioms present with the help of python scripts, along with their usage description, in accordance with the Oxford dictionary.

Visit Project Site

Voting – Fraud Analysis using Web Scraping

A research-based project that utilizes web scraping principles in Python along with the data repository of a people intelligence service of the country, for detecting voting frauds throughout US.

Visit Project Site

Psychiatric Chatbot

A chatbot created using Python and NLP, which works like a psychiatrist and provides all sorts of emotional &mental support.

Visit Project Site

IoT based Pollution Predictor and Plotter

Python based project that uses machine learning algorithm along with SciKit-learn and d3.js libraries. It uses MQ135 & MCP3008 interfaced with Raspberry Pi to collect pollution data (LPG, CO & Smoke) and predict the pollution levels in real time.

Visit Project Site

Stock Market Analysis

This project uses both SQL and HIVE to analyze the stock market data taken from Yahoo Stocks. It then compares the efficiency with which both the languages can process a query and produce the desired results. It uses SQOOP to obtain the data from the dataset to HDFS.

Appointment Scheduler Web Application

This project is built on the Django framework. The application maintains a list of the scheduled appointments and it can perform the CRUD functions on all the objects. Bootstrap3 was used to design the frontend of the application.

Visit Project Site

Python Web Scraping

This is a web scrapping project, developed using the BeautifulSoup library of python. It scrapes the data from a website and uses python libraries such as, Pandas and NumPy to analyze the data that was scraped. Matplotlib library is used to add graphical visualizations.

Website Modelling, Development and Deployment

Created a website using AWS EC2 services and WordPress development tools to showcase the hi-definition games and other attractions offered by a Gaming Company.

Diabetes Patient Readdmission Prediction

The dataset represents 10 years (1999-2008) of clinical care at 130 US hospitals and integrated delivery networks to analyze the Patient Readdmission Frequnecy and reason behind it.

Visit Project Site
0 Years of Study
0 Projects Completed
0 Subjects Completed
0 Cups of coffee


Contact

Contact Me

Contact Number

+ 1-(703)-980-3162

Email Address

arorasaksham96@gmail.com

Website - LinkedIn

Saksham Arora