Machine Learning Data Management

Disha Dhake

848-***-**** Edison, NJ **********.**@*****.*** LinkedIn GitHub

Summary

Results-driven Data & Analytics Professional with 4+ years of experience in data management, reporting, and process optimization across food and academic environments. Skilled in handling large datasets, performing data validation, and conducting statistical analysis using Excel, food industry tools like LIMS, and HPLC systems while ensuring compliance with ISO 17025 standards. Experienced in developing SOPs, dashboards, and quality documentation to enhance audit readiness and operational efficiency. Demonstrated collaboration and communication through team supervision, technical writing, cross-functional coordination, and client engagement. Completed a Master’s in Business Analytics with academic training in Python, Machine Learning, and Power Platform tools to support data-driven business solutions. Education

University at Albany, SUNY Albany, NY

Master of Science in Business Analytics (GPA: 3.7) Aug 2023 – Dec 2024 North Maharashtra University Maharashtra, India

Bachelor of Food Technology July 2012 – April 2016 Technical Skills and Certifications

Core Technical Skills:

• Data Management & Validation:

LIMS, HPLC (OpenLab), Excel (Pivot

Tables, VLOOKUP, Statistical

Analysis), Data Cleaning &

Transformation

• Quality Systems & Compliance:

ISO 17025 Standards, FSSAI

Guidelines, Calibration & QA

Auditing, SOP Documentation,

Traceability

• Reporting & Visualization: Excel

Dashboards, MS Office 365, KPI

Tracking, Trend Analysis

• Process Optimization &

Collaboration: Workflow Mapping

(Lucidchart), Fit-Gap & Root Cause

Analysis, Process Improvement

Training & Certifications:

• Programming & Analytics: Python (Pandas, NumPy,

Scikit-learn, TensorFlow), R, SQL (Queries, Joins, Data Extraction & Analysis)

• Data Visualization & Automation: Tableau (Certified), Power BI (Advanced Dashboards), Power Apps (Canvas Apps & Connectors), Power Automate, Copilot Studio

(Gen AI Flows)

• Machine Learning & AI: Model Development

(Regression, Decision Trees, XGBoost, BERT, LSTM), Model Evaluation (ROC-AUC, F1 Score, Precision/Recall)

• Business Analysis & Design: BPMN/UML Modeling,

Wireframing (Figma, Balsamiq), Requirements Elicitation

& Process Modeling

• Collaboration & Cloud Platforms: JIRA, Confluence, Azure DevOps, M365, Slack, Google Workspace

• Certifications: BPMN/UML, Power Platform (Copilot Studio, Power Apps, Power Automate), Wireframing

(Figma/Balsamiq)

Academic Projects

1. Transformers and News Classification using BERT Link Mar 2024 – May 2024

• Played a pivotal role implementing BERT model for news classification, a 95% validation accuracy through rigorous model training and optimization.

• Developed and deployed the model using Python, TensorFlow, and Hugging Face's Transformers library.

• Preprocessed and transformed a dataset of over 120,000 news articles from the AG corpus using NLTK and BERT's tokenizer.

• Analyzed model performance, showing BERT's superior results compared to LSTM Neural Networks in multi-class text classification.

• Prepared detailed project reports and presentations, outlining methodologies, results, and the impact on text classification in digital media.

2. Vehicle insurance Claims Classification using Python Link Oct 2023 – Nov 2023

• Leveraged data mining techniques to predict if a policyholder would file a claim within the next 6 months.

• Preprocessed insurance claim data using Python, including removing irrelevant columns, extracting numerical values, creating new features, and encoding categorical variables.

• Applied SMOTE to balance the dataset, ensuring robust model training with a well-represented minority class

• Split the cleaned dataset into training and validation sets for rigorous model evaluation.

• Trained and optimized various machine learning models, including Logistic Regression, Naive Bayes, Neural Networks, Decision Trees, and XGBoost, for insurance claim prediction.

• Assessed models using precision, recall, F1 score, and AUC-ROC, and visualized the ROC curve for high predictive accuracy

• Employed Python libraries like Scikit-learn and Imbalanced-learn for model training and evaluation, and Matplotlib and Seaborn for data visualization and reporting. Academic Experience

Professional Development & Academic Engagement Jan 2025 - Current Multiple Academic & Professional Hubs Edison, NJ

Pursuing advanced training and academic collaborations aligned with Business/Data Analytics and AI.

• Completing certification programs in Data & AI Foundations and Business Analysis to strengthen analytical and technical skills.

• Assisting in data-driven research and reporting activities within academic and professional networks.

• Continuing practical learning through case studies, workshops, and analytics projects relevant to career advancement in data and business analysis.

Graduate Assistant – Decision Analytics and Optimization Aug 2024 - Dec 2024 State University of New York Albany, NY

Supported the Decision Analytics & Optimization course by mentoring students, conducting lab sessions, and delivering hands-on training in SDLC, process modeling, and documentation using Lucidchart, wireframing tools, and MS Office.

• Delivered instructional support through group discussions, lab sessions, and one-on-one mentoring, enhancing student understanding of requirements elicitation, process modeling, SDLC, and system design using real-world case studies.

• Conducted hands-on training in tools such as Lucidchart, wireframing platforms, and MS Office, guiding students to create BRDs, use cases, mockups, and process flow diagrams aligned with industry standards.

• Developed learning materials and provided structured feedback on student deliverables, improving documentation clarity and fostering practical skills in data analysis, business requirements, and planning. Professional Experience

Analyst Oct 2021 - Dec 2022

TUV India Pvt. Ltd. Pune, India

Led analytical operations and data validation for food-testing workflows, ensuring accuracy, compliance, and efficiency across ISO 17025 and FSSAI standards. Streamlined QA processes through LIMS automation, Excel- based statistical analysis, and Power BI dashboards, enhancing traceability, reducing turnaround time, and enabling data-driven decision-making for management.

• Analyzed and interpreted large datasets from HPLC and Excel to ensure food-testing accuracy and compliance with ISO 17025 and FSSAI standards.

• Applied statistical methods to identify trends and anomalies, optimizing testing processes and reducing turnaround time by 20%.

• Utilized LIMS for result validation, traceability, and accurate data reporting across QA workflows.

• Developed and standardized SOPs and quality documentation, improving audit readiness and process transparency.

• Built Excel- and Power BI-based dashboards to present key performance and compliance insights to R&D. Sr. Analyst Feb 2021 - Aug 2021

Astute Labs Pvt. Ltd. Pune, India

Managed daily lab operations and data reporting using LIMS while ensuring adherence to quality standards. Partnered with QA and operations teams to streamline workflows, enhance accuracy in analytical testing, and strengthen client communication, contributing to faster project completion and improved team efficiency.

• Operated LIMS software to manage, validate, and report analytical results for food parameters while maintaining compliance with ISO 17025 standards.

• Calibrated and maintained laboratory instruments, ensuring precision, data accuracy, and adherence to quality control protocols.

• Implemented workflow and training improvements that boosted team productivity, reduced turnaround time by 20%, and improved client communication through timely reporting.

• Collaborated with cross-functional team, ensuring on-time delivery of analytical projects and seamless collaboration across QA and operations.

Analyst Dec 2017 - Dec 2020

Vimta Labs Ltd. Pune, India

Executed end-to-end data management for HPLC analyses using OpenLab and LIMS, ensuring data integrity. Automated Excel templates for sample tracking, statistical analysis, and reporting, improving accuracy and efficiency. Supported calibration, SOP updates, and audit readiness to strengthen process traceability and quality control.

• Performed data acquisition and validation of HPLC results using OpenLab and maintained data integrity within LIMS under ISO 17025 guidelines.

• Conducted data cleaning, transformation, and verification to generate accurate and compliant analytical datasets for reporting.

• Designed and maintained Excel databases and automated templates for sample tracking, trend analysis, and statistical evaluation (mean, SD, RSD).

• Created analytical reports and visual summaries in Excel and Word to communicate test findings and insights to QA and client teams.

• Supported process improvement and calibration activities, updating SOPs and audit-ready documentation to enhance workflow efficiency and traceability.

Contact this candidate