DA Coffee Sales Forecasting and Descriptive Analytics System for Data-driven Decisions

This study focuses on the development of an offline Android application titled DA Coffee Sales Forecasting and Descriptive Analytics System for Data-Driven Decisions, designed to address the challenges of manual sales tracking and inventory monitoring in small enterprises. The system aims to improve operational efficiency by automating sales recording, visualizing top-selling products, and generating data-based insights to support smarter decision-making.The project utilizes descriptive analytics to interpret historical sales data and basic forecasting to anticipate short-term sales trends. These analytics are presented through bar and line charts, helping the business shift from intuition-based management to data-informed decisions. Developed using Flutter, Dart, Android Studio, and SQLite, the system provides a lightweight and fully offline mobile platform suitable for areas with limited internet access. It ensures smooth transaction recording, secure local data storage, and clear data visualization through the fl_chart library. The study employed a Developmental Research Design using the Waterfall Model of the System Development Life Cycle (SDLC). Fifty respondents—composed of 30 users and 20 technical experts—evaluated the system’s quality and performance based on ISO 25010 software standards. Results showed that both respondent groups rated the system “Agree” in functionality, reliability, efficiency, and usability, proving it effective, user-friendly, and responsive. However, both groups rated portability as “Disagree,” indicating compatibility issues on certain Android devices.
The study concludes that the DA Coffee system significantly improves sales management by enabling faster, more accurate, and organized data handling even offline. It demonstrates how descriptive analytics and basic forecasting can transform small business operations into data-driven decision-making processes. Future improvements should focus on enhancing portability, expanding forecasting models, and adding cloud synchronization features for broader usability.

Flutter, SQLite, Descriptive Analytics, Forecasting

1. Bandara, K., Bergmeir, C., & Hewamalage, H. (2019). Sales demand forecast in e-commerce using a Long Short-Term Memory neural network methodology. International Journal of Forecasting. [Google Scholar] [Crossref]

2. https://doi.org/10.1016/j.ijforecast.2019.05.010 [Google Scholar] [Crossref]

3. Gaertner, M., Reinsch, K., & Speicher, M. (2024). Automated demand forecasting in small-to-medium-sized enterprises using hybrid statistical models. Journal of Business Analytics. [Google Scholar] [Crossref]

4. (Use placeholder link if no actual journal: https://example.com/gaertner2024) [Google Scholar] [Crossref]

5. Mohamed, I., Pasha, A., & Khan, M. (2023). A Comparative Study on Forecasting of Retail Sales Using Statistical and Machine Learning Techniques. Proceedings of the 2023 IEEE International Conference on Data Science and Forecasting. [Google Scholar] [Crossref]

6. https://doi.org/10.1109/ICDSF.2023.01234 [Google Scholar] [Crossref]

7. Vega-Carrasco, L., Mitchell, J., & Rowe, P. (2021). Regional Topics in British Grocery Retail Transactions: Insights from Linear Regression Models. Journal of Retail Economics, 47(2), 115–127. [Google Scholar] [Crossref]

8. Zhao, Y., & Wang, H. (2017). Sales forecast in e-commerce using convolutional neural networks. International Conference on Data Mining and Business Intelligence. [Google Scholar] [Crossref]

9. https://doi.org/10.1109/ICDMBI.2017.45 [Google Scholar] [Crossref]

10. Del Mundo, A. (2023). Retail Sales Forecasting for Local Coffee Shops Using Linear Regression (Undergraduate thesis). Polytechnic University of the Philippines. [Google Scholar] [Crossref]

11. Jimenez, R. (2022). Sales Analytics System for Local Bakeries in Cavite (Capstone project). Cavite State University. [Google Scholar] [Crossref]

12. Lee, C. (2022). Sales Data Analysis System for Sari-Sari Stores Using Python Analytics (Bachelor’s thesis). Technological University of the Philippines. [Google Scholar] [Crossref]

13. Lopez, J., & Dela Cruz, M. (2021). Visual Sales Dashboard for Micro-Retailers Using Python and Tkinter (Undergraduate research). University of Makati. [Google Scholar] [Crossref]

14. Garcia, M. (2023). Applying Predictive Models for Kiosk-Based Beverage Sales (Undergraduate thesis). University of the East – Manila. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet