HariChandhana Kalikiri

1. ImperialDade : Led an NLP project utilizing LLM models like Deberta, which was successfully deployed to production.

• Implemented the project using Databricks, PySpark, and Pandas
• Managed products from 49 companies acquired by company X, clustering similar products and creating golden records
• Leveraged record linkage and clustering techniques, while also creating features such as color and material using Deberta and Roberta LLM models
• Utilized various scores, including partial scores and between text scores, to enhance clustering accuracy and remove ambiguity

2. ARS : Developed a demand forecasting accelerator which works as plug and play tool that includes modules for data ingestion, data treatment, EDA, univariate forecasting, multivariate forecasting and post-processing of output

• Developed a demand forecasting model to predict booked, bookable, and leadsrun demand, utilizing time series analysis and statistical modeling techniques
• The model successfully forecasted demand trends, aiding in strategic decision-making and resource allocation.

3. T-mobile :Developed an architecture for determine which network KPIs influence customer activations and deactivations at the CBG level using weighted customer mobility data(Casual Analysis) .

• Collected network performance metrics (coverage, capacity, call drops, throughput, latency, etc.) and customer metrics (activations, deactivations) along with mobility data.
• Used customer mobility data to weight activations and deactivations to account for the influence of mobility patterns on these metrics. Aggregate and process data at the CBG level, ensuring it is cleaned, normalized, and prepared for analysis.
• Apply statistical and machine learning models to identify which network KPIs ,upgrades and new site openings significantly influence weighted activations and deactivations.

• Developed KPI's and presented it to management which led to execution plan
• Developed action plans to mitigate risks in decision making while increasing profitability by leveraging data science
• Implemented predictive models using Ml tools
• Submitted POC on Detecting Performance Anomalies in Cellular Networks and developed an alert generating application.
• Assisted with day-to-day operations, working efficiently and productively with all team members.

• Worked on dealer app
• Workflow involves warranty of products, claims, coverage
• MongoDB, Vuejs, Nodejs, were used to develop the application and AWS Amplify for deployment
• Utilized product data to develop and implement a sales forecasting model
• Analyzed historical sales data, product features, and market trends to forecast future sales accurately
• The model contributed to improved inventory management and strategic decision-making.

• Developed a classroom application using VueJS, NuxtJS, Tailwind css
• Implemented Query Resolution System, a platform in which queries raised will be automatically mapped to employees
• Implemented a POC for a plagiarism check model designed to analyze assignment submissions, ensuring originality and integrity of the content
• Developed a classification model for sentiment analysis of product reviews.