AI Pharmacy Inventory Optimization Platform

@sajjadtaghvaeifr

Hello, I trust you're doing well. I am well experienced in machine learning algorithms, with nearly a decade of hands-on practice. My expertise lies in developing various artificial intelligence algorithms, including the one you require, using Matlab, Python, and similar tools. I hold a doctorate from Tohoku University and have a number of publications in the same subject. My portfolio, which showcases my past work, is available for your review. Your project piqued my interest, and I would be delighted to be part of it. Let's connect to discuss in detail. Warm regards. please check my portfolio link: https://www.freelancer.com/u/sajjadtaghvaeifr

@kamran2012

Interesting project, I will deliver a Python/FastAPI platform with your SQL Server backend covering live inventory across three+ branches, dynamic reorder alerts with expiry and shelf life logic, and a hybrid optimization engine that beats your manual baseline by the 10% target on the supplied CSV dataset. On a similar pharmacy build, separating the optimization engine into its own microservice cut forecast refresh times to under two seconds, well within your five second dashboard requirement. Questions: 1) For the Phase 1 decision engine, do you already have logic documented for distinguishing provisional vs. special order items, or will we define that together? 2) Which ERP system is running on the staging server so I can plan the sync hooks early? Ready to start whenever you are. Kamran

@mayankinnovative

Hello You need a developer to build an AI powered pharmacy inventory optimization platform to manage stock demand and reduce wastage. I can design and develop a complete intelligent system for this I will build a platform that tracks inventory in real time analyzes sales and purchase data and uses AI models to predict demand and optimize stock levels AI based pharmacy systems use historical sales data expiry dates and supplier patterns to forecast demand and automate reorder decisions reducing stockouts and overstocking I will implement features like demand forecasting smart reorder alerts expiry tracking analytics dashboard and automated workflows for inventory management The system will also include batch level tracking supplier integration and reporting so you get full control over inventory and operations I will use scalable backend architecture with FastAPI or similar stack along with machine learning models for accurate predictions and performance I focus on building reliable data driven systems that can handle large datasets and improve over time with continuous learning I have experience working with AI systems backend development and building automation platforms A few questions 1 What type of pharmacy data do you have available 2 Do you need real time prediction or periodic forecasting 3 Any preferred tech stack or AI approach 4 Do you need multi store or single location support Thanks

@ASSAMWEB

Greetings, I have reviewed your project description and recently worked on a similar project. I believe I can help you deliver this successfully. Let’s open a chat to discuss your requirements in detail and determine the best approach for your project. Regards

@ERPHarborCS

Hello, I already built something like this for my overseas customers. Your project aligns well with my experience building inventory and ERP-integrated business applications in Python. Although my background includes extensive ERP implementations, my approach is platform-agnostic, and I can build this as a standalone solution that integrates seamlessly with your existing ERP via APIs. I will develop a robust engine that: * Generates purchase requirements using configurable stocking logic (sales frequency + last sold date) * Excludes promotional/offer sales from demand calculations * Handles provisional and special-order items * Checks pending Purchase Orders and GRNs * Considers warehouse availability before purchasing * Recommends optimal inter-branch stock transfers * Produces the final Purchase Order ready for ERP synchronization The solution will be built using **Python (FastAPI)** and **SQL Server**, with a modular architecture so the AI optimization engine can be introduced in later phases without disrupting core operations. The code will be clean, well-documented, and delivered with setup scripts, tests, and user/admin documentation. I believe in iterative development, so I'll demonstrate each milestone for your review and incorporate feedback before moving forward. I would be happy to discuss your stocking rules, ERP integration, and historical data so we can deliver measurable improvements over your current process. Looking forward to working with you.

@ashinnd84

Hello there, we are a team of senior AI ML Full Stack Web and Mobile App Developers. Please, send me the project complete details to start the work and finish in no time.

@techsty2014

Hi, We will build your pharmacy inventory platform on FastAPI and SQL Server: real-time branch tracking, dynamic reorder alerts, and a hybrid optimization engine combining rule-based constraints with ML demand forecasting. For the decision engine, we will separate regulatory and shelf-life rules from the ML layer. The rule engine handles expiry, pending POs, GRNs, and inter-branch transfer logic. The ML layer trains on your historical CSV to refine reorder points per SKU per branch. This split makes each component testable on its own. A couple of quick things to confirm: 1) Which ERP are we syncing with, and does it expose a REST or SOAP API? 2) How many SKUs per branch should we plan for when designing the SQL Server schema? The number quoted here is a starting estimate. Looking forward to talking through the details. Faizan

@mahads31

As an accomplished full-stack developer with a proven track record in Python, I’m confident that I'm the right person for your AI Pharmacy Inventory Optimization Platform. Having deep knowledge in Python and SQL Server, I can ensure you receive a high-end, end-to-end platform that addresses every aspect of your needs. My experience and expertise provide me with a strong understanding of balancing the core functionalities like real-time inventory tracking, automated reorder alerts, hybrid optimization engine, role-based access, and seamless API hooks you require to synchronize with your existing ERP system. In addition to my technical proficiency, I prioritise clear communication at each stage of development — from identifying your requirements to producing concise user/admin documentation. I am always ready to clarify details or provide quick iterative reviews to assure you the deliverables meet your expectations. Lastly, I bring a holistic approach to technology development. I understand that efficient systems are more than just functional components — they are tools designed if well for long-term growth. My focus is nunca only on the present deliverable but also on its flexibility and scalability for future needs. This commitment can be best demonstrated through my long-lasting relationships with clients, like you hope to establish as an esteemed partner of mine!

@deepanshug38

Hello, I'm interested in developing your AI-powered pharmacy inventory optimization platform. Your requirements closely match my experience with Python, FastAPI, SQL, REST APIs, machine learning, and analytics-driven applications. I can build a scalable solution featuring real-time inventory tracking, rule-based reorder logic, ML-powered demand forecasting, role-based access control, and a modular architecture that supports future enhancements. The platform can be designed with FastAPI services, SQL Server integration, and clean REST APIs for seamless ERP connectivity. For Phase 1, I can develop the inventory decision engine to generate purchase requirements, evaluate stock across branches and warehouses, check pending POs/GRNs, recommend inter-branch transfers, exclude special-order or promotional items where required, and generate optimized purchase orders based on configurable business rules. My focus is on clean, maintainable code with proper documentation, Git version control, and a structured implementation approach. The deliverables will include well-commented source code, setup instructions, and user documentation to ensure easy deployment and maintenance. Before starting, I'd like to understand your ERP system and available API documentation so the integration can be planned efficiently. I’m available to discuss the project architecture, milestones, and timeline, and can begin immediately. Best regards, Deepanshu

@jaroslavcaprata

Hi, The key challenge here isn't building an inventory dashboard—it's creating a decision engine that consistently produces better purchasing recommendations than manual planning while integrating cleanly with your ERP. That means combining deterministic business rules with ML forecasting in a way that's transparent, auditable, and easy to validate. I would design the platform with FastAPI-based services, SQL Server as the transactional source of truth, and a separate optimization service for forecasting and inventory recommendations. The rule engine would handle regulatory constraints, expiry dates, pending POs/GRNs, warehouse availability, and inter-branch transfers, while the ML layer would continuously improve demand forecasts using your historical data. Every recommendation would be traceable, with role-based permissions, audit logs, and secure ERP synchronization through REST APIs. To meet your acceptance criteria, I'd validate the optimizer against the supplied historical dataset, measure improvement over the baseline, and ensure the architecture remains modular so forecasting models and business rules can evolve independently. One question before defining the implementation: what ERP system are you integrating with, and does it already expose REST APIs for purchase orders and stock transfers, or will custom integration be required? Jaroslav Caprata

@nexvative

Hi, I can build this Python + SQL Server pharmacy inventory and AI optimisation platform with a strong focus on real-time stock visibility, intelligent replenishment, expiry-aware decisions, and ERP automation. My approach would include: • FastAPI-based services with Python for business logic and AI components. • SQL Server integration using efficient queries, stored procedures, and ORM where appropriate. • Real-time multi-branch inventory dashboard with role-based access and complete audit trails. • Dynamic reorder alerts based on demand, sales frequency, stock coverage, pending POs/GRNs, warehouse stock, and configurable rules. • Hybrid optimisation engine combining deterministic pharmacy/shelf-life constraints with ML demand forecasting and inter-branch transfer recommendations. • Phase 1 decision engine covering purchase requirements, offer exclusions, provisional/special-order items, pending orders, warehouse availability, transfers, and final PO generation. • Secure ERP API integration for one-click purchase order and stock-transfer synchronisation. I’ll build the system modularly so the optimisation engine can scale independently, with clean APIs, logging, configuration, tests, and documentation. I’ll also validate the engine against your historical CSV data and benchmark it against your existing manual rules.

@shayankhan333

The hardest part of pharmacy inventory optimization isn't the forecasting model, it's preventing the optimizer from recommending transfers of items near expiry that just shift waste between branches. That constraint needs to live inside the decision engine from day one, not bolted on later. I'll build this on FastAPI with a dedicated microservice for the optimization engine, keeping it decoupled so it scales independently. Phase 1 will cover the full inventory decision pipeline: purchase requirement generation, stocking logic based on frequency and last-sold data, offer exclusions, provisional/special-order handling, pending PO and GRN checks, warehouse stock validation, inter-branch transfer recommendations, and final PO output. Best regards, Shayan

@hoangvanp

Hello, Creating an AI-powered pharmacy inventory optimization platform involves more than just tracking stock levels. It's about ensuring seamless operations across multiple branches by leveraging real-time data and AI algorithms. By focusing on automated reorder alerts and a hybrid optimization engine, we can enhance demand forecasting and cost management while maintaining compliance with regulatory and shelf-life constraints. Utilizing Python for business logic and FastAPI for services, we can build a scalable solution that synchronizes seamlessly with your ERP system. I have experience in developing similar systems that prioritize efficiency and accuracy in inventory management. By carefully considering the technical requirements and acceptance criteria, we can deliver a robust solution that exceeds expectations. A few questions: - How is the current data structured in your SQL Server? - Are there any specific regulatory constraints we should be aware of? - Have you encountered any challenges with inventory management in the past that we should address? Best regards,

@alluankit01

Hi, I can build Phase 1 of your AI pharmacy inventory optimization platform using Python/FastAPI and SQL Server, focused on live stock visibility, purchase requirements, reorder logic, inter-branch transfers, and ERP-ready PO generation. The best solution is to first review your SQL Server schema, ERP flow, branch inventory rules, historical sales CSV, offer-sale logic, provisional/special-order handling, pending PO/GRN rules, and warehouse stock structure. I’ll then build a modular inventory decision engine with clean APIs, audit logs, role-based access, and optimization logic that can later expand into ML forecasting. I’m comfortable with Python, FastAPI, SQL Server, stored procedures/ORM mappings, ERP integrations, inventory optimization, demand forecasting, branch-level stock logic, REST APIs, Git, dashboards, and data analytics. Deliverables will include: * Inventory decision engine * Purchase requirement generation * Dynamic reorder alerts * Pending PO/GRN checks * Warehouse stock checks * Offer-sale exclusion logic * Provisional/special-order handling * Inter-branch transfer recommendations * Final PO generation * Admin/Inventory Manager roles * Audit logs and documentation * Setup scripts and Git repository I’ll focus on a stable Phase 1 foundation that reduces manual inventory decisions, supports three simulated branches, and prepares the platform for ML forecasting and ERP sync in later milestones. Best regards Ankit

@Hrolgar

Which signal wins when a near-expiry batch at one branch could cover a shortage at another through a transfer, but that branch already has a pending PO landing in two days? That's the kind of conflict the decision engine has to resolve deterministically, and explain afterward in the audit trail, not just optimize on paper. I'd build this as a staged FastAPI service over SQL Server, starting with the core decision logic: demand, expiry, cost, and inter-branch stock feeding one scoring pass that outputs purchase requirements, transfer recommendations, and draft POs, with pending POs and GRNs treated as committed supply so the engine never double orders. RBAC and audit trails sit on the same schema from day one, so every recommendation traces back to the inputs behind it. ERP sync and the dashboards layer on once that core proves out against your actual edge cases. The number below is a first pass off the brief. It'll move once I know what your ERP exposes, a real-time API versus batch exports changes how much of M3 is integration versus polling. M1: Core decision engine (demand, expiry, cost scoring, PO/transfer logic), 24750 INR, 7 days M2: Forecasting, inter-branch optimization, RBAC + audit trails, 27000 INR, 8 days M3: ERP sync, dashboards, edge case hardening, 23250 INR, 6 days M1 on its own gets you the engine making real calls on your data before the rest gets scoped or paid for.

@adriank06

Hi there, After reviewing the requirements for your multi-branch inventory platform, it is clear that the success of this project hinges on two critical technical pillars: highly optimized database architecture for real-time performance, and a robust hybrid model for the AI optimizer. As a backend and AI developer specializing in data-intensive applications, here is my technical approach for delivering Phase 1 and ensuring we meet your strict acceptance criteria: 1. Service Architecture & The <5-Second Challenge To guarantee the dashboard refreshes live stock across multiple simulated branches in under five seconds, relying solely on Python ORMs (like SQLAlchemy) will create bottlenecks. Backend Layer: I propose using FastAPI for the services layer. It is extremely lightweight, asynchronous, and perfectly suited for microservice architectures. Database Layer: All transactional data will remain securely in SQL Server. I will implement highly optimized Stored Procedures and structured indexing to handle the heavy lifting (filtering offer sales, aggregating warehouse stock, and evaluating pending POs/GRNs). This minimizes payload transfer times and ensures lightning-fast dashboard updates. 2. The Hybrid Optimization Engine (Targeting >10% Improvement) Isolating the optimizer in its own microservice is the right approach for scalability. Rule-Based Logic: Hard constraints—such as regulatory limits, shelf-life, frequency of sales, provisional items, and current warehouse stock—will act as strict filters to ensure absolute compliance. ML Forecasting Layer: To beat the baseline manual rules by at least 10%, I will implement a robust time-series forecasting model trained on your provided CSV historical dataset. This layer will balance purchase costs against expiry risks and dynamically recommend inter-branch transfers to minimize dead stock and optimize capital. 3. ERP Synchronization & Security (RBAC) Seamless Integration: The platform will feature secure, documented API hooks designed to push approved purchase orders and inter-branch transfer requests directly to your staging ERP without manual intervention. Role-Based Access Control: I will implement strict permission layers. Inventory Managers will be able to trigger POs, but system settings will be hard-locked to Admins. Every action will be tied to a comprehensive audit trail. Phase 1 Deliverables: You will receive a well-documented repository containing the Decision Engine microservice, SQL setup scripts/stored procedures, environment configurations, and concise documentation. The logic will be built to successfully pass your provided test suite of edge-case scenarios. I am highly available for iterative reviews after each milestone. I would love to discuss the structure of your historical CSV dataset and the specific edge cases for Phase 1. Best regards

@sanket99799

Hi, I'm Sanket, with experience building Python-based business applications, ERP integrations, AI automation, and SQL Server solutions for inventory and operational management. For Phase 1 – Inventory Decision Engine, I'll develop a scalable architecture using Python (FastAPI) and SQL Server, designed for seamless ERP integration and future AI optimization. Key deliverables: Real-time multi-branch inventory dashboard Purchase requirement generation based on sales frequency and last sold date Exclusion of offer sales from demand calculations Handling of provisional and special-order items Validation against pending POs, GRNs, and warehouse stock Intelligent inter-branch transfer recommendations Automated final Purchase Order generation Role-based access with audit logging REST APIs for ERP synchronization The solution will be modular, allowing future expansion with ML-based demand forecasting, expiry optimization, and advanced inventory balancing. I'll deliver clean, documented code, SQL scripts, API documentation, deployment instructions, and a Git repository for easy maintenance. I'd be happy to discuss your ERP architecture and historical inventory workflow to ensure the recommendation engine aligns with your business processes and performance requirements. Best Regards, Sanket

@Tacticssoft

Hello, I am an experienced Python and SQL Server developer specialising in inventory systems, ERP integrations, automation, and AI-powered optimisation. I can build the Phase 1 Inventory Decision Engine to generate accurate purchase requirements and final purchase orders. The system can analyse sales frequency, last-sold data, pending POs, GRNs, warehouse stock, provisional items, special orders, and offer sales exclusions. I can also implement intelligent stocking logic and recommend optimal inter-branch stock transfers. Python with FastAPI and SQL Server would provide a scalable architecture with efficient database queries, stored procedures, and clean API integrations. I can design the engine with clear, testable business rules so each decision is traceable and easy to audit. The solution can later be extended with machine-learning demand forecasting and optimisation without rebuilding the core system. I will provide clean, well-commented code, setup scripts, documentation, and a structured Git repository. I am comfortable working with ERP APIs and can prepare the system for reliable one-click purchase order and stock transfer synchronisation. I would be happy to review your current SQL Server structure, ERP integration requirements, and Phase 1 test data to define the implementation plan and milestones.

@NEHABHAT92

Having garnered over 9+ years of experience in web and mobile development, I believe I'm perfectly positioned to create the AI Pharmacy Inventory Optimization Platform. My expertise in Python will be instrumental in driving the business logic and AI components of the platform, while my experience with SQL Server will ensure efficient storage and retrieval of all transactional data. The comprehensive understanding I've developed over the years of handling E-commerce and CMS-based websites aligns well with your project's objective to balance demand, expiry dates, and purchase costs across branches. I understand that this harmony requires not only rule sets but an AI layer, and I'm confident my proficiency can deliver the promised improvements in demand forecasts, transfer suggestions, and optimisation, beating manual rules by at least 10%, as required. One key aspect of project success is seamless integration with your existing ERP system. My previous experiences mirror this requirement, having worked on projects where synchronisation with other systems was crucial. My unyielding commitment to excellent quality work coupled with a customer-centric approach means I'll ensure not just successful API hooks for pushing approved purchase orders and stock transfers but also a comprehensive user/admin documentation to make your life easier after project completion.