Geethanjali Sanikommu Research Profile

About

Geethanjali Sanikommu is a skilled Software Developer with over six years of professional experience in designing, developing, and maintaining software solutions using diverse technology stacks. Her expertise spans across Java, MuleSoft, RPA technologies like Blue Prism and Foxtrot, and API management. With a strong understanding of the Software Development Life Cycle (SDLC) and hands-on experience in Agile and Waterfall methodologies, Geethanjali has successfully delivered projects for notable organizations, including Flagstar Bank and Volkswagen. She is proficient in creating RAML-based APIs, deploying Mule flows on CloudHub, and securing APIs effectively. Additionally, Geethanjali has experience in mobile application development for both Android and iOS, along with extensive knowledge of database management using MySQL, Oracle, and PostgreSQL. Known for her analytical skills, teamwork, and problem-solving abilities, Geethanjali is dedicated to building reliable, efficient, and innovative software solutions.

Skills

Experience

WEB APPLICATION DEVELOPER

Flagstar Bank

Sep-2021 to Present

Education

Grand Valley State University

Master of Science (MS) in Computer Information Systems

Passout Year: 2019

Peer-Reviewed Articles

Data Management Strategies and Machine Learning Applications in the Indian Financial Industry: A Comprehensive Study

The effective management of data has emerged as a critical requirement in the modern financial industry, particularly in the Indian context where the sector experiences exponential data growth, regulatory complexities, and a rapidly evolving technological landscape. This paper aims to explore comprehensive data management strategies within Indian financial institutions, including banks, insurance companies, stock exchanges, and fintech startups, while integrating modern data science, machine learning (ML), and artificial intelligence (AI) techniques. By combining traditional data governance principles with contemporary analytical methodologies, this research presents an integrative framework that enhances decision-making, risk management, customer profiling, and regulatory compliance. Our methodology employs a mixed-method approach comprising quantitative data analysis from financial transactions, customer databases, and regulatory reports, alongside qualitative insights drawn from expert interviews across financial hubs such as Mumbai, Bengaluru, and Kolkata. Data is sourced from publicly available financial databases, institutional archives, and primary research involving structured interviews with senior data managers. Sampling combines purposive and stratified techniques to ensure representation across public, private, and fintech sectors. Analytical techniques range from statistical modeling and regression analysis to machine learning classification models for fraud detection and predictive analytics for credit scoring. Findings reveal that Indian financial institutions struggle with legacy system integration, data silos, and fragmented governance frameworks. However, organizations that have adopted advanced data pipelines, real-time analytics platforms, and AI-driven risk models exhibit superior agility, compliance adherence, and customer satisfaction. Furthermore, we identify significant variance in data maturity across different financial segments, with fintech companies showcasing more innovative data strategies compared to traditional banking entities. Three comprehensive tables capture industry-wise data practices, comparative data management strategies, and machine learning adoption levels. This study contributes to the literature by proposing a data governance-maturity model tailored to the Indian financial landscape, integrating regulatory alignment, technological advancement, and organizational culture. The research underscores the importance of aligning data management strategies with evolving regulatory norms such as those set by RBI, SEBI, and IRDAI, ensuring data privacy, customer-centric innovation, and operational resilience. In conclusion, the research advocates for a cross-sector collaborative approach, wherein regulatory bodies, financial institutions, and technology providers co-create dynamic data ecosystems that foster innovation while ensuring systemic stability. This research offers practical insights for data managers, policymakers, and technologists navigating the intersection of finance, data science, and machine learning in India’s evolving financial ecosystem.

Advanced Data Management and Analytics in the Pharmaceutical Industry: Leveraging Machine Learning and Big Data for Enhanced Decision-Making

The pharmaceutical industry stands at the intersection of healthcare innovation and technological advancement, making efficient data management an imperative for accelerating drug discovery, regulatory compliance, supply chain optimization, and patient safety. This research paper, titled "Advanced Data Management and Analytics in the Pharmaceutical Industry: Leveraging Machine Learning and Big Data for Enhanced Decision-Making," presents a comprehensive exploration of how modern data management frameworks and advanced analytics, particularly machine learning (ML) and big data analytics, are transforming pharmaceutical operations. The purpose of the research is to investigate and develop a multi-dimensional data management framework, integrating structured and unstructured data across research and development, clinical trials, manufacturing, and post-market surveillance. A mixed-method approach was adopted, combining quantitative data analysis from clinical databases, real-world evidence (RWE) repositories, and pharmaceutical manufacturing logs with qualitative insights from expert interviews across major Indian pharmaceutical firms such as Dr. Reddy’s Laboratories, Sun Pharmaceutical Industries, and Lupin Limited. Data collection leveraged electronic health records (EHRs), laboratory information management systems (LIMS), supply chain systems, and regulatory compliance databases. Sampling was conducted using purposive stratified techniques to ensure representation across diverse pharmaceutical functions, from drug discovery to distribution. Analytical techniques included descriptive statistics, supervised machine learning algorithms such as Random Forest and Gradient Boosting for predictive modeling, and unsupervised clustering for pattern discovery within clinical trial and supply chain data. Key findings reveal that machine learning models significantly enhance predictive accuracy in clinical trial outcomes and supply chain disruptions. Real-time data ingestion pipelines, coupled with natural language processing (NLP) algorithms applied to regulatory documents, streamline regulatory submissions and compliance monitoring. Ethical considerations included data anonymization, informed consent in patient data usage, and strict adherence to Good Clinical Practice (GCP) and General Data Protection Regulation (GDPR). The research contributes to the field by proposing a novel Pharmaceutical Data Management (PDM) Framework, which harmonizes real-time analytics, secure data sharing, and predictive modeling capabilities. This framework supports adaptive clinical trials, real-time pharmacovigilance, and personalized medicine initiatives. The study concludes with a discussion on the integration challenges, including data silos, legacy system interoperability, and evolving regulatory requirements. Practical implications include improved R&D productivity, reduced time-to-market for new therapies, enhanced supply chain resilience, and more effective post-market surveillance. The proposed framework, validated through expert reviews and pilot testing, offers a scalable and customizable model for pharmaceutical enterprises globally. In summary, this paper bridges the gap between data science and pharmaceutical operations, demonstrating how data-driven decision-making powered by advanced analytics can transform the industry’s operational efficiency, innovation capacity, and regulatory compliance.

Enhancing Data Reporting Efficiency Using Machine Learning Techniques in Real-Time Analytics

The modern data-driven economy relies heavily on real-time analytics and seamless data reporting processes, which have become pivotal across sectors including finance, healthcare, e-commerce, and manufacturing. Efficient data reporting not only facilitates timely decision-making but also enhances the accuracy and relevance of organizational intelligence. This paper explores the intersection of advanced data reporting practices and machine learning techniques, focusing on how real-time data pipelines can be optimized for efficiency, accuracy, and scalability. With the exponential growth of data, traditional methods often fall short in processing and analyzing streaming data in real-time. Our research investigates the integration of machine learning algorithms into automated data reporting systems to improve data validation, anomaly detection, and reporting accuracy. We designed a hybrid research approach comprising both quantitative and qualitative methods, including analysis of operational data from industry leaders in retail, banking, and manufacturing sectors, as well as structured interviews with data engineers and analysts. Sampling covered large organizations with diverse data infrastructures, and analysis incorporated techniques such as regression analysis, clustering, and natural language processing (NLP) for real-time text summarization. Ethical considerations focused on data privacy, consent, and algorithmic fairness. Results show that integrating machine learning with real-time data reporting can reduce data processing errors by 37%, enhance anomaly detection accuracy by 42%, and accelerate report generation time by 63%. Our tables highlight comparisons across industries, system architectures, and error reduction techniques. These findings bridge key gaps in existing literature, which either focus on static data reporting or siloed machine learning implementations. This study’s implications extend to data governance policies, system design best practices, and future advancements in predictive analytics for proactive reporting enhancements. The paper also outlines limitations such as computational overhead, interpretability challenges, and data privacy concerns, all of which open avenues for further research into federated learning, edge analytics, and explainable AI in real-time reporting contexts. By advancing methodologies for data reporting, this research contributes directly to improving operational efficiency and analytical agility in data-intensive environments, particularly for data science teams tasked with balancing speed, accuracy, and compliance

Cloud Data Warehousing: Transforming Scalable Data Management and Analytics for Modern Enterprises

Cloud data warehousing has emerged as a revolutionary solution addressing the ever-increasing needs of data management, real-time analytics, and scalable storage for businesses across industries. This research comprehensively investigates the paradigm shift from traditional on-premises data warehouses to cloud-based solutions, emphasizing their role in data science, machine learning workflows, and real-time decision-making. The objective of this paper is to assess the technical, operational, and economic benefits of cloud data warehouses and their direct impact on data-intensive applications in fields like e-commerce, finance, healthcare, and logistics. Through a mixed-methods approach involving primary data collection from enterprises using AWS Redshift, Google BigQuery, Snowflake, and Azure Synapse, supplemented with secondary literature, the study captures insights into deployment strategies, performance optimization techniques, and governance practices. Quantitative data is derived from performance benchmarks, while qualitative data reflects the perceptions of IT managers, data scientists, and infrastructure architects. Statistical methods including regression analysis, ANOVA, and clustering techniques provide insights into cost-performance trade-offs, latency patterns, and scalability factors. Ethical considerations such as data privacy, regulatory compliance, and responsible AI integration are also explored. Findings indicate that cloud data warehousing reduces infrastructure costs by up to 50%, enhances query performance by leveraging distributed architectures, and accelerates machine learning model training pipelines through seamless data access. The research contributes to the evolving discourse on hybrid and multi-cloud data strategies, emphasizing the importance of data integration, workload portability, and vendor lock-in mitigation. By presenting empirical data, case studies, and expert opinions, this paper provides a comprehensive understanding of how cloud data warehousing serves as a foundational pillar in modern data ecosystems, supporting both operational analytics and advanced data science initiatives. The study concludes with recommendations for optimizing data warehouse performance, improving data governance frameworks, and aligning cloud data strategies with business goals to maximize return on investment and competitive advantage.

Examining The Study Habit of Single Parent Children and Their Academic Performance

Background: Single-parent households are increasingly common, and their impact on children's development has been a subject of extensive research. While single parents often face unique challenges, including financial strain and increased household responsibilities, their children's academic outcomes are not universally negative. This study aims to investigate the relationship between study habits and academic performance in children from single-parent families. Method: A sample of 150 students from single-parent households studying in class X was recruited from various schools in Garo Hills region. Data were drawn by using scale on study habit and academic report card were used to generate data for the study. To accomplish this, the researchers employed survey method as a research design Results: No significant differences were found in overall study habits between children from single-parent and two-parent households. However, some specific study habits, such as time management and organizational skills, showed a trend towards being slightly lower in the single-parent group. No significant differences were found in overall academic performance between the two groups. Relationship between Study Habits and Academic Performance: Strong positive correlations were found between study habits and academic performance in both groups, indicating that effective study habits are crucial for academic success regardless of family structure.

Conference/Seminar/STTP/FDP/Symposium/Workshop

Conference

May 2023

Informatica world 2023

Hosted By:

Informatica Corporation ,

Las Vegas, Nevada, United States

Certificates

Issued : Jan 2019

By : SAS Institute

SAS Certified Base Programmer for SAS 9

Scholar9 Profile ID

S9-032025-0109919

Publication

(0)

Article Reviewed

(12)

Citations

(0)

Network

(0)

Conferences/Seminar

(1)

Mrs. Geethanjali Sanikommu