Full-Stack Developer, Data Science, Machine Learning & AI ...
US Only job Attach your similar projects.
We are looking is have an innovative system designed to optimize purchase decisions for a small business specializing in the refurbishment and sale of IT products, such as laptops and PCs, across multiple online platforms (Amazon, eBay, Shopify). The system aims to use data-driven insights to rank products based on profitability and stock levels... facilitating smarter buying decisions. It will feature interactive 'Buying Requirement Sheets for use by purchasing team members, historical purchase records, and supplier data to assist purchasers in the buying process. It will also provide various detailed sales analysis reports as well as employing machine learning to spot golden nuggets or likely areas of increased profitability.
Technical Scope: Full-Stack Development: Build a user-friendly interface for inputting and displaying data, integrating with real-time sales feeds, and managing user access based on credentials and IP.
Data Science & Analysis: Implement algorithms to analyse sales data, calculate profit and loss in real time, and project future sales trends.
Machine Learning: Develop models to identify patterns in sales data, suggesting products with the highest return on investment based on historical performance and market trends.
Requirements:
Experience in building scalable full-stack applications, preferably with knowledge of Python, R, Node.js, Express, and relevant front-end technologies.
Proficiency in data manipulation and analysis tools (e.g., Pandas, NumPy) and machine learning libraries (e.g., Scikit-Learn, TensorFlow).
Familiarity with database management (PostgreSQL, MySQL) and cloud platforms (AWS, Azure, Google Cloud) for deploying and scaling applications.
Understanding of e-commerce dynamics and the ability to integrate with FileMaker Pro (internal) and external APIs (Amazon, eBay, Shopify) for real-time data fetching.
Project Goals:
1. Dynamic Profit & Loss Calculation: Real-time tracking of sales and costs to determine profitability.
2. Purchase Recommendation System: Use current stock levels and profitability projections to generate ranked buying lists.
3. Historical Data Analysis: Leverage past purchase and sales data to forecast trends and inform buying decisions.
4. Machine Learning Insights: Identify profitable product characteristics and optimize inventory based on predictive analytics.
Data Handling:
- Real-time and historical sales and cost data integration.
- Automated and manual data entry options for cost and sales price adjustments.
- Security measures for data access and manipulation.
Considerations:
- The interfaces should be intuitive for users with varying levels of technical expertise.
- The system will augment existing processes (e.g., FileMaker Pro for production flow and management), requiring seamless data exchange capabilities.
- AI as a future extension to become involved in purchasing - searching and finding stock.
Closing:
We are seeking a dynamic Full-Stack Developer with expertise in Data Science and Machine Learning & AI more widely to join our project. The ideal candidate will bring innovative solutions to complex problems, helping us achieve our goal of maximizing profitability through data-driven decision-making.
Machine Learning Insights:
The core of our machine learning initiative within PERCY is to uncover hidden trends and profitability factors across a vast array of product categories and characteristics. Our inventory, including refurbished and upgraded items, spans numerous categories (e.g., laptops) and sub-categories (e.g., laptops-traditional, laptops-DELL), with each products featuring up to 25 distinct characteristics. These characteristics range from hardware specifications (Manufacturer, CPU Generation, Screen Resolution, SSD size, etc.) to sales channels (Amazon UK, eBay Germany, Shopify, etc.).
Our objective is for the machine learning model to analyse these dimensions to identify highly profitable and fast-selling combinations of characteristics. For instance, discovering that laptops with a 7th Gen CPU, VPRO capability, and 2TB Gen 4 NVME drives yield 30% higher profits and sell 50% faster than other configurations would be invaluable. Such insights will enable us to prioritize refurbishing efforts and inventory purchases towards the most lucrative products, significantly impacting our ROI and sales velocity.
This machine learning functionality will not only automate the identification of profitable trends but also adapt to evolving market conditions, ensuring our buying and refurbishing strategies remain ahead of the curve
Apply Now
We are looking is have an innovative system designed to optimize purchase decisions for a small business specializing in the refurbishment and sale of IT products, such as laptops and PCs, across multiple online platforms (Amazon, eBay, Shopify). The system aims to use data-driven insights to rank products based on profitability and stock levels... facilitating smarter buying decisions. It will feature interactive 'Buying Requirement Sheets for use by purchasing team members, historical purchase records, and supplier data to assist purchasers in the buying process. It will also provide various detailed sales analysis reports as well as employing machine learning to spot golden nuggets or likely areas of increased profitability.
Technical Scope: Full-Stack Development: Build a user-friendly interface for inputting and displaying data, integrating with real-time sales feeds, and managing user access based on credentials and IP.
Data Science & Analysis: Implement algorithms to analyse sales data, calculate profit and loss in real time, and project future sales trends.
Machine Learning: Develop models to identify patterns in sales data, suggesting products with the highest return on investment based on historical performance and market trends.
Requirements:
Experience in building scalable full-stack applications, preferably with knowledge of Python, R, Node.js, Express, and relevant front-end technologies.
Proficiency in data manipulation and analysis tools (e.g., Pandas, NumPy) and machine learning libraries (e.g., Scikit-Learn, TensorFlow).
Familiarity with database management (PostgreSQL, MySQL) and cloud platforms (AWS, Azure, Google Cloud) for deploying and scaling applications.
Understanding of e-commerce dynamics and the ability to integrate with FileMaker Pro (internal) and external APIs (Amazon, eBay, Shopify) for real-time data fetching.
Project Goals:
1. Dynamic Profit & Loss Calculation: Real-time tracking of sales and costs to determine profitability.
2. Purchase Recommendation System: Use current stock levels and profitability projections to generate ranked buying lists.
3. Historical Data Analysis: Leverage past purchase and sales data to forecast trends and inform buying decisions.
4. Machine Learning Insights: Identify profitable product characteristics and optimize inventory based on predictive analytics.
Data Handling:
- Real-time and historical sales and cost data integration.
- Automated and manual data entry options for cost and sales price adjustments.
- Security measures for data access and manipulation.
Considerations:
- The interfaces should be intuitive for users with varying levels of technical expertise.
- The system will augment existing processes (e.g., FileMaker Pro for production flow and management), requiring seamless data exchange capabilities.
- AI as a future extension to become involved in purchasing - searching and finding stock.
Closing:
We are seeking a dynamic Full-Stack Developer with expertise in Data Science and Machine Learning & AI more widely to join our project. The ideal candidate will bring innovative solutions to complex problems, helping us achieve our goal of maximizing profitability through data-driven decision-making.
Machine Learning Insights:
The core of our machine learning initiative within PERCY is to uncover hidden trends and profitability factors across a vast array of product categories and characteristics. Our inventory, including refurbished and upgraded items, spans numerous categories (e.g., laptops) and sub-categories (e.g., laptops-traditional, laptops-DELL), with each products featuring up to 25 distinct characteristics. These characteristics range from hardware specifications (Manufacturer, CPU Generation, Screen Resolution, SSD size, etc.) to sales channels (Amazon UK, eBay Germany, Shopify, etc.).
Our objective is for the machine learning model to analyse these dimensions to identify highly profitable and fast-selling combinations of characteristics. For instance, discovering that laptops with a 7th Gen CPU, VPRO capability, and 2TB Gen 4 NVME drives yield 30% higher profits and sell 50% faster than other configurations would be invaluable. Such insights will enable us to prioritize refurbishing efforts and inventory purchases towards the most lucrative products, significantly impacting our ROI and sales velocity.
This machine learning functionality will not only automate the identification of profitable trends but also adapt to evolving market conditions, ensuring our buying and refurbishing strategies remain ahead of the curve
Apply Now