Retail and Consumer Packaged Goods

Retail and Consumer Packaged Goods

Retail and consumer goods organizations need predictive analytics and optimization in today’s world because the landscape is so competitive. Companies able to target specific consumers with offers based on their current location, past purchasing history, demographic information in real-time with offers steeped in pricing revenue optimization will gain significant marketplace separation. Look at the success of companies like Amazon!

Many organizations have embraced analytics. Living in such a diverse, data loaded enterprise with elements of logistics, marketing, pricing, supply chain, manufacturing, and strategic planning, can leave an executive’s head spinning. With so many decisions to make it is no wonder data analytics is quickly becoming a necessity in the retail world.

Mosaic is a great strategic partner for companies in the retail and consumer goods vertical. We bring world-class big data analytics consulting and model development capabilities to be more data-driven in all facets of the business. Our data science consultants bring cutting edge machine learning, statistical, and data engineering techniques to transform business questions into analytically-fueled solutions that bring competitive advantage.

We work with some of the World’s leading Retail and Consumer Goods brands

Leading Outdoor Retailer – Inventory Optimization

  • This retailer wanted to turn towards a more predictive data-driven strategy for making seasonal inventory purchasing decisions.
    • Made decisions only based on historical sales data.
  • Mosaic used predictive analysis techniques to discover insights, which the inventory team was than able to translate into making better buying decisions.
  • Delivered an automated model which recommends product specific order distributions across sizes, styles and colors.
  • Decreases markdowns and increases revenue.

Link to full case study.

Leading Brick and Mortar Retailer – Price Elasticity of Demand 

  • Innovative pricing for >160 million seasonal products.
    • Explore and model different promotional pricing approaches to increase seasonal clothing revenue, decrease stock-outs, and minimize close-out pricing.
    • Calculate how elastic demand was, what seasonality patterns drive demand for each type of item.
  • Developed nonlinear regression techniques to compute demand and to provide confidence intervals from longitudinal and cross-sectional data.
  • Delivered open-source developed R Shiny decision support dashboard.
    • What-If scenarios feature easy to understand impact of potential changes.

Link to full case study.

Neiman Marcus – Online behavior modeling from a cold start

  • Proof of Concept to enhance customer experience, predict demand patterns and sell more product at the right price for individual customers.
    • Explore and implement non-parametric choice models to help client understand consumer demand patterns.
  • Data analyzed included web browsing data, brand-specific product data, and transactional data.
  • The results of this model were useful in showing how different consumer types and their preference rankings inform buyer decisions.

Leading Alcoholic Beverage Distributor and Manufacturer 

  • Objective: to help better understand trends in state and brand-level craft beer trends.
  • Mosaic quantified metrics that provide more clarity to differentiate states according to current craft maturity and rate of growth/development.
    • Developed K-means clustering model of states using novel metrics, including appropriate visualizations of clusters and metrics within each cluster.
    • Developed a hierarchical clustering model using same metrics to provide alternate description of state-level data.
  • Delivered a summary of statistical relationships between metrics, clusters, and appropriate visualizations of trends within each cluster, and list of states in each hierarchically-derived cluster and appropriate visualizations of tends within each cluster.

Leading Soft Drink and Snack Distributor and Manufacturer – Analytics Assessment & Daily Store-Order Prediction

  • Analytics readiness assessment services.
    • Help move from a business intelligence, reactive framework to a framework which can support analytics, and deliver insights to business users.
  • Daily Store-Order Prediction Model developed and implemented
    • Predicting store demand accurately is a major industry challenge. Mosaic Data Science, a consultancy specializing in advanced analytics, is uniquely positioned to tackle and create applicable solutions.
    • Mosaic data scientists developed a short-horizon predictive model that forecasts the case-quantity orders at a SKU-store level on the day of an account manager’s store visit
      • This architecture combines the predictions of the above three models and selects the one performing best based on historical model performance. Because the three models complement each other in characterizing certain behavior of the case quantities, this model generally provides the most intelligent information and can adjust to pattern changes over time such as when a SKU moves from mainline to secondary status in a store or when a new account manager is assigned to a store.
  • The prediction model and automated insights more accurately predict correct store orders, providing efficient and intelligent results.

Link to full case study.

Contact Mosaic today to learn more.