International Peer-Reviewed JournalOpen AccessISSN 2456-8880
irejournals@gmail.com+91-7433024337

Home / Current Issue / Paper 1722333

1722333 Vol 10 · Issue 2 Download Paper

Demand-Sensing RTM for Independent Grocers: A Lightweight Analytics Framework Using POS and ERP Events

John Dima Tariro Lyan Nhemachena Watson Jameson Muponda Lisa Tsveta Munashe Naphtali Mupa

Subject area: Management and Commerce  ·  Area of research: Accounting and Auditing

Abstract

Independent grocers and small retail distributors operate at the intersection of volatile local demand, constrained working capital, limited analytics capacity and costly replenishment decisions. This study develops and evaluates a lightweight demand-sensing route-to-market (RTM) framework that can be implemented using ordinary point-of-sale (POS) and enterprise resource planning (ERP) events. Using the public Kaggle Store Item Demand Forecasting Challenge structure, comprising five years of daily sales records for 50 items across 10 stores, the study engineers calendar, lag, rolling-demand and promotion-proxy features to compare seasonal naive, linear and machine-learning forecasting logic. The strongest demand-sensing model achieved MAE of 4.43, RMSE of 5.54 and sMAPE of 12.54%. In the replenishment simulation, demand sensing reduced estimated stockout exposure by 30.5% compared with a lag-7 heuristic, while changing the average order index by -0.8%. The paper contributes a pragmatic RTM analytics architecture, a decision workflow for independent grocers, and an evidence-based implementation roadmap linking demand forecasting to inventory availability, delivery frequency, cash conversion and supplier-service decisions.

Keywords

demand sensing, route-to-market, independent grocers, retail analytics, POS data, ERP, inventory optimization, machine learning, SME supply chains, stockouts

How to cite this paper

John Dima, Tariro Lyan Nhemachena, Watson Jameson Muponda, Lisa Tsveta, Munashe Naphtali Mupa "Demand-Sensing RTM for Independent Grocers: A Lightweight Analytics Framework Using POS and ERP Events" Iconic Research And Engineering Journals Volume 10 Issue 2 2026 Page 1991-1999
John Dima, Tariro Lyan Nhemachena, Watson Jameson Muponda, Lisa Tsveta, Munashe Naphtali Mupa "Demand-Sensing RTM for Independent Grocers: A Lightweight Analytics Framework Using POS and ERP Events" Iconic Research And Engineering Journals, vol. 10, no. 2, Aug. 2026
John Dima, Tariro Lyan Nhemachena, Watson Jameson Muponda, Lisa Tsveta, Munashe Naphtali Mupa (2026). Demand-Sensing RTM for Independent Grocers: A Lightweight Analytics Framework Using POS and ERP Events. Iconic Research And Engineering Journals, 10(2).
John Dima, Tariro Lyan Nhemachena, Watson Jameson Muponda, Lisa Tsveta, Munashe Naphtali Mupa "Demand-Sensing RTM for Independent Grocers: A Lightweight Analytics Framework Using POS and ERP Events" Iconic Research And Engineering Journals, vol. 10, no. 2, Aug. 2026.
@article{1722333,
      author = {John Dima, Tariro Lyan Nhemachena, Watson Jameson Muponda, Lisa Tsveta, Munashe Naphtali Mupa},
      title = {Demand-Sensing RTM for Independent Grocers: A Lightweight Analytics Framework Using POS and ERP Events},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {2},
      pages = {1991-1999},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722333.pdf},
      abstract = {Independent grocers and small retail distributors operate at the intersection of volatile local demand, constrained working capital, limited analytics capacity and costly replenishment decisions. This study develops and evaluates a lightweight demand-sensing route-to-market (RTM) framework that can be implemented using ordinary point-of-sale (POS) and enterprise resource planning (ERP) events. Using the public Kaggle Store Item Demand Forecasting Challenge structure, comprising five years of daily sales records for 50 items across 10 stores, the study engineers calendar, lag, rolling-demand and promotion-proxy features to compare seasonal naive, linear and machine-learning forecasting logic. The strongest demand-sensing model achieved MAE of 4.43, RMSE of 5.54 and sMAPE of 12.54%. In the replenishment simulation, demand sensing reduced estimated stockout exposure by 30.5% compared with a lag-7 heuristic, while changing the average order index by -0.8%. The paper contributes a pragmatic RTM analytics architecture, a decision workflow for independent grocers, and an evidence-based implementation roadmap linking demand forecasting to inventory availability, delivery frequency, cash conversion and supplier-service decisions.},
      keywords = {demand sensing, route-to-market, independent grocers, retail analytics, POS data, ERP, inventory optimization, machine learning, SME supply chains, stockouts},
      month = {August},
  }