Wyze Labs

Applying Machine Learning and Deep Learning to Quantify Text Data to Project Forecasts of NPI and Mature Products

This student team will work to: 1. Develop fundamental forecast models for Wyze's maturing products (1-2 product lines) and NPI (1-2 product lines). 1.1. Research and conduct data analytics and quantify the text data (e.g. industry reports, market surveys, consumers' feedback, macro economy environment, consumer buying power, etc.) into variables in the forecast analysis, by establishing machine learning/deep learning models. 1.2. Explore, identify, and quantify the impact of additional factors (like competitor products, consumers demographics, etc). 2. Conduct scenario analysis on supplies and inventory management (e.g. supply/replenishment volume arrangement, local inventory level management, financial resources management). 2.1. Quantify the impact of forecast errors on the supplies (e.g. if forecast misses 20%, the impact on inventory and supplies management). 2.2. Develop supply chains strategies (e.g. safety stock planning, cycle stock planning, continuous supplies etc) to supplement NPI sales, if forecasts under-/over-estimate the real sales. 2.3. Linear programming/optimizations on balancing financial resources minimizations and sufficient supplies. Design parameters and performance this student team will work to integrate include: 1. Historical sales data (volume and prices) provided by Wyze. 2. Industry data - ISE student consultants 3. Text data (consumers' feedback, media blogs, youtuber's video, etc) - ISE student consultants Outcomes this student team will work to achieve include: 1. Fundamental forecast models (actively control the forecast errors within +/- 20%). 2. Comprehensive analysis on the impact of forecasts fluctuations on supplies/inventory management. 3. Optimization models to minimize the usage of financial resources, or maximize supplies volume to avoid stock outs.