Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM64461
Volume:
10 |
6 |
Jun 2026
Pages:
1-9
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Data Engineering
Independent Researcher
Grocery stores face a continuous operational challenge in balancing product availability with waste reduction. Fast-moving products may go out of stock before store teams notice, leading to missed sales and poor customer experience. At the same time, fresh products may remain on shelves too long and expire before they are sold, creating food waste and financial loss. Traditional dashboards help visualize inventory and sales trends, but they often require business users to interpret charts manually and decide the next action. This research presents Grocery Data Intelligence, a Data + AI-driven grocery inventory planning system built on a modern data engineering lakehouse architecture. The proposed system converts raw grocery data into trusted business metrics and action recommendations using a layered Bronze, Silver, Gold, and semantic data design. The application enables users to analyze stockout risk, waste risk, days of supply, reorder needs, promotion opportunities, and donation possibilities through dashboards, natural language questions, inventory storytelling, and action workflows. The system was designed using Databricks Free Edition as an experimental platform for building a practical Data + AI solution. The architecture demonstrates how clean data engineering foundations can support business-ready insights, natural language analytics, and faster decision-making. Unlike traditional reporting systems, Grocery Data Intelligence moves beyond static dashboards by helping store users understand what is happening, why it matters, and what action should be taken. This paper explains the problem background, architecture, implementation approach, methodology, expected outcomes, and future enhancements of the proposed system. The findings show that combining data engineering, trusted metrics, semantic definitions, and AI-powered interaction can help grocery businesses reduce stockouts, reduce waste, improve planning, and move from insight to action faster.
KEYWORDS
This paper presented Grocery Data Intelligence, a Data + AI-driven grocery inventory planning system built on a lakehouse architecture. The system addresses a practical retail problem: reducing stockouts and waste by converting raw grocery data into trusted metrics and recommended actions. The research demonstrates how data engineering and AI can work together to support faster business decisions. The Bronze layer stores raw data, the Silver layer cleans and standardizes data, the Gold layer prepares business metrics, and the semantic layer provides consistent definitions. The application then uses these trusted metrics to power dashboards, natural language questions, inventory storytelling, and action workflows. The project shows that the future of analytics is not limited to reporting. Data should help users understand what is happening, why it matters, and what action should be taken. Grocery Data Intelligence follows this direction by moving from dashboard visibility to decision support. The findings indicate that Data + AI solutions can help grocery stores plan better, reduce stockouts, reduce waste, and act faster. The approach can also be extended to other retail and supply chain domains where timely action is critical.
Armbrust, M., et al. (2021). Lakehouse: A New Generation of Open Platforms that Unify Data Warehousing and Advanced Analytics. Proceedings of the VLDB Endowment, 14(12), 3183–3196.Databricks, Inc. Delta Lake Documentation. Available at: https://delta.ioDatabricks, Inc. Databricks Free Edition Documentation. Available at: https://docs.databricks.comDatabricks, Inc. Databricks Apps Documentation. Available at: https://docs.databricks.comDatabricks, Inc. Lakebase Postgres Documentation. Available at: https://docs.databricks.comDatabricks, Inc. AI/BI Genie Documentation. Available at: https://docs.databricks.comKimball, R., & Ross, M. (2013). The Data Warehouse Toolkit: The Definitive Guide to Dimensional Modeling. Wiley.Chopra, S., & Meindl, P. (2019). Supply Chain Management: Strategy, Planning, and Operation. Pearson.Silver, E. A., Pyke, D. F., & Thomas, D. J. (2016). Inventory and Production Management in Supply Chains. CRC Press.Russell, S., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach. Pearson.
Publication Date
6/3/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...