Description:FIELD OF THE INVENTION
[0001] The present invention relates to the field of inventory management, and more particularly, the present invention relates to the Block chain enabled demand forecasting and inventory optimization for drug store.
BACKGROUND FOR THE INVENTION:
[0002] The following discussion of the background to the invention is intended to facilitate an understanding of the present invention. However, it should be appreciated that the discussion is not an acknowledgment or admission that any of the material referred to was published, known, or part of the common general knowledge in any jurisdiction as of the priority date of the application. The details provided herein the background if belongs to any publication is taken only as a reference for describing the problems, in general terminologies or principles or both of science and technology in the associated prior art.
[0003] Pharmacies and drug stores often face critical challenges in managing their inventories efficiently. These include:
- Unpredictable demand caused by seasonal illnesses, pandemics, or public health events.
- Overstocking, which leads to expiry-related losses and high carrying costs.
- Stock-outs, which delay patient care and reduce customer satisfaction.
- Manual inventory practices prone to human errors and inefficiencies.
- Lack of real-time forecasting, resulting in delayed decision-making.
- No transparent traceability of inventory events, making regulatory compliance difficult.
[0004] The present solutions include:
- Tally / Marg ERP Software: Offers basic inventory, billing, and GST-compliant accounting features. No blockchain support.
- Excel or Google Sheets Forecasting: Used for manual forecasting based on previous sales trends. Time-consuming, error-prone, and non-scalable.
- Zoho Inventory / QuickBooks Commerce: Cloud-based tools for inventory tracking and order management. Integrates with e-commerce platforms. No pharmaceutical-specific features or prediction models.
- Forecast Pro / Demand Works Smoothie: Standalone forecasting software using statistical models. Good for large datasets and time series analysis. Requires data science skills; no integration with inventory systems.
- Amazon Forecast / Google AutoML Tables: AI-as-a-Service platforms for custom demand forecasting. Accurate, scalable ML models. Requires technical expertise and cloud dependency. No domain-specific customizations (e.g., pharma expiry, batch control).
- Mobile Apps for Inventory (e.g., Pharmarack, MedCords): Used for distributor-pharmacy stock sync. Useful for small vendors. No analytics, prediction, or audit trail features.
[0005] Traditional inventory systems are reactive and static, relying heavily on historical averages and manual restocking rules. These approaches are inadequate for today’s dynamic and data-rich healthcare environment.
[0006] KR20240143003A: The invention offers a method for managing a plurality of pharmacies that is characterized by the following: a step in which a pharmaceutical management server is connected to a plurality of management devices within a pharmacy. The pharmaceutical management server receives sales information and stock information on pharmaceuticals from each of the plurality of management devices within the pharmacy and updates the information in a database. The pharmaceutical management server then obtains inventory information on pharmaceuticals in each of the plurality of pharmacies based on the sales information or the stock information.
[0007] US8285607B2: A product inventory management system that comprises a cabinet that is designed to house an inventory of product units with RFID tags and is further configured to monitor the inventory by wirelessly detecting the RFID tags. The server system is configured to communicate with the cabinet over a network and is capable of managing the cabinet's inventory. Additionally, there is a method for product inventory management that involves the receipt of inventory data from a cabinet through a network and a server system. This data corresponds to an inventory of product units stored in the cabinet, and an order is generated to add additional product units to the cabinet in accordance with the cabinet inventory.
[0008] AU2021101706A4: Our proposed system consists of two modules: a block chain-based drug supply chain management system and a machine learning-based drug recommendation system. Aspects of the present disclosure pertain to the method (100) for drug delivery using the blockchain 5 technique. The drug supply chain management system is implemented in the initial module. However, we employ a variety of applications to suggest the most effective or highly rated medications to the pharmaceutical industry's customers. These models have been trained on a well-known drug evaluations dataset, which can be accessed through an open-source machine learning repository. Furthermore, this system is combined with the machine learning module through the use of a REST API.
[0009] In light of the foregoing, there is a need for the Block chain enabled demand forecasting and inventory optimization for drug store that overcomes problems prevalent in the prior art.
OBJECTS OF THE INVENTION:
[0010] Some of the objects of the present disclosure, which at least one embodiment herein satisfies, are as follows.
[0011] The principal object of the present invention is to overcome the disadvantages of the prior art by providing the Block chain enabled demand forecasting and inventory optimization for drug store.
[0012] Another object of the present invention is to provide the Block chain enabled demand forecasting and inventory optimization for drug store that cmbines SARIMAX for capturing seasonality and LSTM for modeling complex, non-linear demand patterns, improving accuracy.
[0013] Another object of the present invention is to provide the Block chain enabled demand forecasting and inventory optimization for drug store that ensures tamper-proof audit trails for every inventory transaction, improving transparency and traceability.
[0014] Another object of the present invention is to provide the Block chain enabled demand forecasting and inventory optimization for drug store that provides a Real-time dashboards for low stock, forecasted demand, and supplier analytics using a React-based UI.
[0015] Another object of the present invention is to provide the Block chain enabled demand forecasting and inventory optimization for drug store that has a Web-based and scalable backend (Node.js, PostgreSQL) that supports real-time access for pharmacists, suppliers, and admins.
[0016] Another object of the present invention is to provide the Block chain enabled demand forecasting and inventory optimization for drug store that provides data privacy and granular access control to different stakeholders.
[0017] Another object of the present invention is to provide the Block chain enabled demand forecasting and inventory optimization for drug store that not only optimizes stock levels and minimizes losses but also meets regulatory standards by logging immutable inventory records, making it ideal for modern pharmacy operations.
[0018] Other objects and advantages of the present disclosure will be more apparent from the following description, which is not intended to limit the scope of the present disclosure.
SUMMARY OF THE INVENTION:
[0019] The present invention provides Block chain enabled demand forecasting and inventory optimization for drug store that presents a comprehensive Drug Store Inventory Prediction System that addresses these challenges through the integration of advanced machine learning algorithms, blockchain technology, and modern web development frameworks. The system using SARIMAX (Seasonal Auto Regressive Integrated Moving Average with Exogenous factors) and LSTM (Long Short-Term Memory) models for accurate demand forecasting, enabling pharmaceutical retailers to optimize inventory levels while minimizing stockouts and overstock situations.
[0020] It includes:
[0021] a) Hybrid AI Model for Demand Forecasting
- Combines SARIMAX (for capturing seasonality and external factors) and LSTM
- (for modeling complex temporal dependencies) in a single system.
- Unlike traditional inventory systems that use simple moving averages or rule-based logic, this hybrid model delivers more accurate and adaptive forecasts.
[0022] b) Blockchain-Backed Audit Trail
- Integrates blockchain (e.g., Ethereum smart contracts) to immutably record inventory transactions, enhancing transparency, trust, and regulatory compliance.
- This ensures traceability and prevents tampering—a feature rarely combined with demand forecasting tools.
[0023] c) AI + Blockchain in One Platform
- Most existing tools either focus on AI-based forecasting or supply chain visibility.
- Our system uniquely integrates both for real-time prediction + secure, tamper-proof tracking.
[0024] d) Modular and Scalable Architecture
- Built using open-source modern tech stack: React (UI), Node.js (backend), PostgreSQL (database), and MetaMask + Solidity (blockchain).
- The architecture is flexible and can be deployed for single stores or large chains.
[0025] e) Role-Based Dashboards and Smart Alerts
- Interactive UI customized for different users (pharmacist, admin, supplier).
- Real-time dashboards display demand forecasts, low-stock alerts, and transaction history—empowering better decisions.
[0026] f) Secure and Regulatory Friendly
- Employs role-based access, data encryption, and smart contract enforcement, making it suitable for pharma compliance scenarios.
BRIEF DESCRIPTION OF DRAWINGS:
[0027] Reference will be made to embodiments of the invention, examples of which may be illustrated in accompanying figures. These figures are intended to be illustrative, not limiting. Although the invention is generally described in the context of these embodiments, it should be understood that it is not intended to limit the scope of the invention to these particular embodiments.
[0028] Figure 1: System architecture along with process flow;
[0029] Figure 2: presents the ER diagram of all the entities in our database.
[0030] Figure 3: Pharmacy Dashboard UI;
[0031] Figure 4: Pharmacy wallet UI;
[0032] Figure 5: Supplier wallet UI;
[0033] Figure 6: Prediction based on category (SARIMAX);
[0034] Figure 7: LSTM Architecture;
[0035] Figure 8: Model loss curve (bones & joints category);
[0036] Figure 9: Model loss curve ( heart & cardiovascular health); and
[0037] Figure 10: Model loss curve (liver health).
DETAILED DESCRIPTION OF DRAWINGS:
[0038] While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and the detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claim.
[0039] As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean "at least one” and the word “plurality” means “one or more” unless otherwise mentioned. Furthermore, the terminology and phraseology used herein are solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers, or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents, acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
[0040] In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase “comprising”, it is understood that we also contemplate the same composition, element, or group of elements with transitional phrases “consisting of”, “consisting”, “selected from the group of consisting of, “including”, or “is” preceding the recitation of the composition, element or group of elements and vice versa.
[0041] The present invention is described hereinafter by various embodiments with reference to the accompanying drawing, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, several materials are identified as suitable for various facets of the implementations. These materials are to be treated as exemplary and are not intended to limit the scope of the invention.
[0042] The present invention provides a Block chain enabled demand forecasting and inventory optimization for drug store that presents a comprehensive Drug Store Inventory Prediction System that addresses these challenges through the integration of advanced machine learning algorithms, blockchain technology, and modern web development frameworks. The system using SARIMAX (Seasonal Auto Regressive Integrated Moving Average with Exogenous factors) and LSTM (Long Short-Term Memory) models for accurate demand forecasting, enabling pharmaceutical retailers to optimize inventory levels while minimizing stockouts and overstock situations. It includes:
[0043] a) Hybrid AI Model for Demand Forecasting
- Combines SARIMAX (for capturing seasonality and external factors) and LSTM
- (for modeling complex temporal dependencies) in a single system.
- Unlike traditional inventory systems that use simple moving averages or rule-based logic, this hybrid model delivers more accurate and adaptive forecasts.
[0044] b) Blockchain-Backed Audit Trail
- Integrates blockchain (e.g., Ethereum smart contracts) to immutably record inventory transactions, enhancing transparency, trust, and regulatory compliance.
- This ensures traceability and prevents tampering—a feature rarely combined with demand forecasting tools.
[0045] c) AI + Blockchain in One Platform
- Most existing tools either focus on AI-based forecasting or supply chain visibility.
- Our system uniquely integrates both for real-time prediction + secure, tamper-proof tracking.
[0046] d) Modular and Scalable Architecture
- Built using open-source modern tech stack: React (UI), Node.js (backend), PostgreSQL (database), and MetaMask + Solidity (blockchain).
- The architecture is flexible and can be deployed for single stores or large chains.
[0047] e) Role-Based Dashboards and Smart Alerts
- Interactive UI customized for different users (pharmacist, admin, supplier).
- Real-time dashboards display demand forecasts, low-stock alerts, and transaction history—empowering better decisions.
[0048] f) Secure and Regulatory Friendly
- Employs role-based access, data encryption, and smart contract enforcement, making it suitable for pharma compliance scenarios.
[0049] It includes Figure1 as system architecture diagram and flow diagram (such as AI-driven inventory system and Blockchain integration modules). The system architecture integrates four main components to enable smart, secure inventory management. The Frontend UI provides role-based dashboards showing real-time inventory levels and demand predictions. It communicates with the Backend API, which handles authentication and CRUD operations. The backend connects to a Machine Learning Engine that uses SARIMAX and LSTM models for accurate demand forecasting. Simultaneously, a Blockchain Integration module logs all critical inventory transactions using Ethereum smart contracts, ensuring transparency and tamper-proof records. Both the ML and blockchain layers interact with a centralized PostgreSQL database for secure data storage and retrieval.
[0050] While the system leverages known components like SARIMAX, LSTM, Ethereum, and smart contracts, their integration in a unified, intelligent pharmacy forecasting and compliance platform represents a non-obvious improvement over existing systems. The following inventive steps distinguish our system:
[0051] Integrated AI-Blockchain Architecture for Inventory Decision-Making: While prior patents explore blockchain or AI individually, our system integrates real-time AI predictions (SARIMAX + LSTM) with blockchain-based transaction records in a modular and fully operational platform, enhancing pharmacy decision-making. Integration is not trivial; it includes real-time coordination between AI forecasts and blockchain events, requiring synchronized event triggers and feedback loops.
[0052] Dual-Layer Blockchain Validation with Forecast Confidence Thresholds: In addition to basic blockchain logging, the system introduces a dual-validation mechanism: a forecast is only written to blockchain if its confidence interval exceeds a set threshold (based on RMSE/MAE). It Ensures that only validated, high-quality predictions become part of the immutable record, improving trust and auditability.
[0053] Smart Contract-Driven Inventory Response Automation: Blockchain smart contracts don’t just log transactions — they also trigger stock alerts, vendor notifications, or reorder workflows based on AI forecast results. Use of smart contracts not as passive recorders but active agents tied directly to forecast outputs and inventory thresholds.
[0054] Cross-Platform, Role-Based Smart Dashboards with Explainability Layer: The system includes a role-based dashboard where each user role (pharmacist, supplier, admin) receives different actionable insights, and integrates explainable AI (XAI) tools like SHAP to display prediction justifications. Prior solutions lack predictive interpretability or role-personalization for decision support.
[0055] Dynamic Model: The system compares SARIMAX and LSTM predictions in real-time, using a loss evaluation module to select the best model dynamically and retrain as required. It enables continuous learning and model adaptability based on evolving demand trends — a step beyond static predictive systems.
[0056] Selector with Self-Tuning Feedback Loop: The system compares SARIMAX and LSTM predictions in real-time, using a loss evaluation module to select the best model dynamically and retrain as required. It enables continuous learning and model adaptability based on evolving demand trends — a step beyond static predictive systems.
[0057] Lightweight, Edge-Compatible Forecasting Engine: system supports deployment on low-cost, edge devices (e.g., Raspberry Pi with ONNX/TFLite) to enable rural or mobile pharmacies to access AI-blockchain insights offline or intermittently connected environments. None of the cited systems consider edge deployment with full AI-blockchain capability.
[0058] The invention provides an AI and blockchain-powered platform that enables pharmacies and drug stores to manage inventory proactively. It forecasts drug demand, flags anomalies, and immutably records inventory actions using smart contracts.
[0059] Historical sales data and external features (Input) like disease outbreaks are fed into ML models: The data such as Drug sales records (date, product, quantity sold), Product details (expiry, category, brand), External features such as: Public health alerts (e.g., flu outbreak), Seasonal patterns (e.g., winter = cough syrups), Weather data, festivals, or local events will be provided as the input for training and updating the machine learning models.
[0060] Demand prediction is generated using SARIMAX and LSTM: The SARIMAX Model Captures seasonality and uses external regressors (e.g., holidays, promotions). Suitable for structured, linear demand trends. LSTM (Long Short-Term Memory), A type of deep learning model designed to capture nonlinear and long-term dependencies. Trained on time-series sales data. It detects patterns in spikes, sudden drops, or slow-moving items and returns a forecasted quantity for each drug for a specific time frame. It includes confidence intervals and prediction accuracy scores.
[0061] Based on forecasted data, inventory thresholds are optimized: The system calculates reorder levels, safety stock, and lead times. Sets automatic restock alerts when inventory approaches minimum thresholds. To prevent both overstocking (leading to waste) and stock-outs (impacting patient care).
[0062] Each inventory transaction is recorded on a blockchain ledger: Each key event (e.g., stock purchase, sale, return, and expiry) is written to the blockchain (e.g., Ethereum testnet). Stored as a smart contract event, including: Product ID, Timestamp, Quantity, Action (e.g., Stock In, Stock Out, and Rejected). Blockchain is used to ensures immutability (can’t be changed), enables auditability (trace every transaction), and provides regulatory compliance and trust.
[0063] Dashboard Displays Predictions, Alerts, and Transaction Logs in Real Time: Built using React.js for pharmacists, suppliers, and administrators. Dashboard features include Forecast charts (per product or category), Low-stock alerts, Blockchain transaction viewer, Supplier performance metrics, Model performance analytics,
[0064] Enables all stakeholders to make informed decisions on: Procurement, Inventory planning, Supplier management, Compliance monitoring.
[0065] Key Components:
- ML Prediction Engine (SARIMAX + LSTM)
- Blockchain Audit Layer
- React Frontend Dashboard
- Node.js + Express.js Backend API
- PostgreSQL Database
- Role-based UI for pharmacists, suppliers, and admins
[0066] Technical Features:
- Dual-model forecasting approach
- Blockchain for regulatory compliance
- Frontend-backend decoupling for scalability
- Real-time inventory health visualization
- Secure and auditable from end to end
[0067] Results from prototype: The dataset used for demonstrating the following outputs is a dummy dataset, intended solely for testing and illustration purposes.
[0068] The Blockchain-Enabled Demand Forecasting and Inventory Optimization System offers significant advantages compared to conventional inventory software and manual machine learning setups. Designed with pharmacists and healthcare stakeholders in mind, this intelligent system combines predictive analytics with blockchain transparency—without requiring deep technical skills.
[0069] Advantages of the present invention:
[0070] a) No Programming Required: Features a user-friendly interface where pharmacists and non-technical users can view predictions, generate reports, and respond to inventory alerts—all without writing code.
[0071] b) Fully Automated Demand Forecasting: Automates the entire machine learning pipeline, including:
- Data preprocessing
- Feature engineering
- SARIMAX and LSTM model selection
- Forecast generation and evaluation
- This enables fast, consistent, and accurate predictions without manual intervention.
[0072] c) Streamlined, Interactive Dashboard: Uses a clean, interactive web dashboard (React-based) to display:
- Stock trends
- Demand forecasts
- Low-stock alerts
- Blockchain-verified transaction history
[0073] d) Designed for Pharmacists and Healthcare Researchers
- Empowers non-technical users in the pharmaceutical field to analyze, manage, and predict inventory independently.
[0074] e) Reduces Human Error in Forecasting and Tracking
- Automates predictions and transaction logging to minimize mistakes in stock planning and audit reporting.
[0075] f) Blockchain-Backed Traceability
- Logs each inventory transaction on a block chain ledger, ensuring tamper-proof records for compliance and audits.
[0076] g) Cost-Effective and Open-Source Tech Stack
- Built using open-source libraries (Scikit-learn, TensorFlow, Web3, PostgreSQL), reducing operational costs and ensuring scalability.
[0077] h) Multi-Model Forecasting Support
- Automatically compares output from SARIMAX and LSTM models for accuracy. Suitable for both short-term and long-term planning in inventory operations.
- It provides an automated, AI forecasting system integrated with blockchain to help pharmacies optimize inventory and reduce loss.
- It promotes data-driven decision-making and operational efficiency in pharmaceutical retail, even for users without AI expertise.
- It is Applicable across drug stores, healthcare retail chains, medical warehouses, and small clinics for inventory control and forecasting.
- It Built on AutoML pipelines, combining statistical (SARIMAX) and deep learning (LSTM) models, with block chain (Ethereum) for audit trails.
- No-Code Simplicity: For pharmacists and store managers.
- Personalized Forecasting: Models adapt to store-specific trends.
- Regulatory Compliance: Block chain-based ledger supports audits.
- Educational Value: Ideal for training healthcare staff on predictive inventory systems.
[0078] The disclosure has been described with reference to the accompanying embodiments herein and the various features and advantageous details thereof are explained with reference to the non-limiting embodiments in the following description. Descriptions of well-known components and processing techniques are omitted so as to not unnecessarily obscure the embodiments herein.
[0079] The foregoing description of the specific embodiments so fully revealed the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the scope of the embodiments as described herein. , Claims:We Claim:
1) A drug store inventory management system, the system comprising:
- a processor, operably coupled to a memory, configured to execute machine learning and inventory management;
- a data acquisition unit, comprising interfaces to accept historical pharmaceutical sales data, drug metadata, and external signals comprising: weather patterns and public health advisories, optionally from a sensor network, local server, or cloud-based API;
- a hybrid demand forecasting engine, implemented on the said processor, comprising:
a SARIMAX model to model structured and seasonal demand trends using exogenous variables, and
a LSTM model to model nonlinear temporal patterns in pharmaceutical consumption data;
- a model selection module, embedded within the processor, configured to evaluate prediction accuracy (based on RMSE/MAE) and dynamically select the better performing model for each product line;
- a blockchain transaction module, configured to execute smart contracts and log pharmaceutical inventory events, including drug receipt, sale, return, or expiry, onto a decentralized blockchain ledger;
- a role-specific user interface unit, comprising a touchscreen-enabled embedded display or web dashboard client, implemented using a React-based interface, configured to show real-time forecasts, low-stock alerts, and blockchain transaction logs;
- an inventory optimization engine, implemented in hardware logic, that computes optimal reorder points, safety stock levels, and supplier recommendations based on forecasted demand; and
- a network interface to enable real-time communication between pharmacists, suppliers, administrators, and external data sources.
2) The system as claimed in claim 1, wherein the blockchain transaction ledger is configured to accept forecast-based entries only when the confidence interval of the forecast exceeds a pre-defined threshold, enabling a dual-layer blockchain validation mechanism.
3) The system as claimed in claim 1, wherein the smart contracts deployed on the blockchain are configured to automatically trigger vendor notifications, low-stock alerts, or reorder requests based on forecasted demand.
4) The system as claimed in claim 1, wherein the model selector module includes a self-tuning feedback loop configured to retrain the selected model periodically based on new incoming data and changing demand patterns.
5) The system as claimed in claim 1, wherein the dashboard includes explainable AI (XAI) features such as SHAP (SHapley Additive exPlanations) visualizations, configured to display model decision logic to end-users.
6) The system as claimed in claim 1, wherein the ML prediction engine and blockchain module are designed to be deployable on edge devices (such as Raspberry Pi) using lightweight AI frameworks (such as ONNX or TensorFlow Lite), enabling rural and offline usage.
7) The system as claimed in claim 1, wherein the forecasting engine utilizes external variables such as weather patterns, public health advisories, and local holidays as exogenous inputs to improve prediction accuracy.
8) The system as claimed in claim 1, wherein said smart dashboard is configured to display role-specific insights including:
- pharmacist: low-stock warnings and reorder suggestions;
- supplier: demand trend reports and expected procurement;
- administrator: audit logs and compliance reports.
9) The system as claimed in claim 1, wherein all inventory events are time-stamped and cryptographically signed to ensure non-repudiation, traceability, and compliance with pharmaceutical audit standards.
10) A method for demand forecasting and inventory optimization in a drug store, the method being executed on a system comprising at least one hardware processor, memory, a network interface, and a blockchain module, the method comprising the steps of:
- collecting and preprocessing historical sales data and exogenous variables;
- generating demand forecasts using both SARIMAX and LSTM models;
- selecting the optimal forecast output based on model performance evaluation;
- optimizing inventory thresholds and reorder points from the forecast;
- recording each inventory transaction on a blockchain ledger through smart contract execution; and
- presenting forecasts, alerts, and transaction logs through a role-based, web-enabled dashboard.