Ravi Teja Pagidoju

Ravi Teja Pagidoju

Althoughthereislittleempiricalresearchonplatform-specific performance for retail workloads, the digital transformation of the retail industry has accelerated the adoption of cloud-based Point-of-Sale (POS) systems. This paper presents a systematic, repeatable comparison of POS workload deployments on Google Cloud Platform (GCP) and Microsoft Azure using real-time API endpoints and open-source benchmarking code. Using free-tier cloud resources, we offer a transparent methodology for POS workload evaluation that small retailers and researchers can use. Our approach measures important performance metrics like response latency, throughput, and scalability while estimating operational costs based on actual resource usage and current public cloud pricing because there is no direct billing under free-tier usage. All the tables and figures in this study are generated directly from code outputs, ensuring that the experimental data and the reported results are consistent. Our analysis shows that GCP achieves 23.0% faster response times at baseline load, while Azure shows 71.9% higher cost efficiency for steady-state operations. We look at the architectural components that lead to these differences and provide a helpful framework for merchants considering cloud point-of-sale implementation. This study establishes a strong, open benchmarking methodology for retail cloud applications and offers the first comprehensive, code-driven comparison of workloads unique to point-of-sale systems across leading cloud platforms.

Ravi Teja Pagidoju, Shriya Agarwal

Planogram creation is a significant challenge for retail, requiring an average of 30 hours per complex layout. This paper introduces a cloud-native architecture using diffusion models to automatically generate store-specific planograms. Unlike conventional optimization methods that reorganize existing layouts, our system learns from successful shelf arrangements across multiple retail locations to create new planogram configurations. The architecture combines cloud-based model training via AWS with edge deployment for real-time inference. The diffusion model integrates retail-specific constraints through a modified loss function. Simulation-based analysis demonstrates the system reduces planogram design time by 98.3% (from 30 to 0.5 hours) while achieving 94.4% constraint satisfaction. Economic analysis reveals a 97.5% reduction in creation expenses with a 4.4-month break-even period. The cloud-native architecture scales linearly, supporting up to 10,000 concurrent store requests. This work demonstrates the viability of generative AI for automated retail space optimization.

Ravi Teja Pagidoju

Standard LSTM(Long Short-Term Memory) neural networks provide accurate predictions for sales data in the retail industry, but require a lot of computing power. It can be challenging especially for mid to small retail industries. This paper examines LSTM model compression by gradually reducing the number of hidden units from 128 to 16. We used the Kaggle Store Item Demand Forecasting dataset, which has 913,000 daily sales records from 10 stores and 50 items, to look at the trade-off between model size and how accurate the predictions are. Experiments show that lowering the number of hidden LSTM units to 64 maintains the same level of accuracy while also improving it. The mean absolute percentage error (MAPE) ranges from 23.6% for the full 128-unit model to 12.4% for the 64-unit model. The optimized model is 73% smaller (from 280KB to 76KB) and 47% more accurate. These results show that larger models do not always achieve better results.