Deloitte Retail Analytics

Deloitte Turkey combines its deep retail experience and know-how in with analytics and help companies in taking data and insight driven decisions.

Retail industry enters in a new era where data is much bigger and valuable. Companies aim to improve analytical capabilities utilizing scientific methods and technological innovations. Integration of retail analytics into strategic and operational decision support systems helps companies to increase margins significantly and create competitive advantages.

Deloitte, combines its deep retail experience and know-how in with analytics and help companies in taking data and insight driven decisions.  Our analytics experts collaborate with experienced retail team in order companies to capitalize on advanced retail analytics. Our team utilizes, global and local know-how, advanced statistical models, data mining tools and broad databases.

Deloitte offers wide range of services in retail analytics and develop customized solutions in any area that will help companies to analyze themselves, market, customers and competition in a more sophisticated way. Our main services are following: Markdown optimization, Price elasticity, Consumer Segmentation, Market Basket Analysis and Promotion Recommendations, Target Market and Location Analysis through Geospatial Analytics, Supply Chain Optimization, Store Clustering and Data Visualization.

  • Number, timing and depth of markdown which are likely to generate the largest possible margin is optimized by advanced analytical models
  • For each SKU, model optimizes:

1. How many: Number of markdown to hold during the sales period aligned with the business requirements

2. How deep: Depth of each markdown

3. How often: Timing of each markdown during the sales period

  • By considering:

1.       Consumers’ reaction to price changes

2.       Stock to clear

3.       Sales rate before and during the markdown, and seasonality 

Markdown Optimization

  • Van Westendorp measures the price sensitivity via market research techniques  to determine the optimum price levels
  • Model is supported by statistical analysis of sales performance and competitive intelligence
  • Models are integrated to demand forecast to maximize the efficiencies in pricing decisions

Price elasticity

  • Consumer segmentation is implemented in multiple dimensions by using Agglomorative Hierarchical Clustering methods (Censydiam Model)
  • Qualitative and Quantitative market researches are conducted and integrated with company and market data
  • Ultimately new market positioning opportunities and brand strategy are identified for companies by analyzing consumer behavior in different segments and creating segment profiles

Strategic Level Consumer Segmentation 

  • Customers are segmented by analyzing purchasing frequency, product preferences, discount preferences obtained from CRM systems and by applying Self Organizing Maps (SOMs) or Kohonen Algorithms.
  • By analyzing consumer behavior in different segments and creating segment profiles, various recommendations such as new promotion alternatives are formulated

Operational Level Consumer Segmentation 

  • Products that are likely to be consumed together in different stores during different time periods (seasons, time of day etc.) are identified through product affinity modeling and relationship visualization techniques by analyzing PoS data.
  • Following the determination of the product consumption behavior of consumers, various menu suggestions, promotional offers, product merchandising offers could be formulated

Market Basket Analysis and Promotion Recommendations

  • Deloitte developed a planning tool that aims to facilitate the pre-season planning processes effectively  at strategic, financial and tactical level.
  • Pre-season planning tool consists strategic and financial planning module, merchandise financial planning and channel/store planning modules and merchandise planning module.
  • High level strategic insights of companies are distributed through the channel and the product dimensions and they can be input for financial plans.
  • More than twenty retail parameter is automatically calculated for each level of planning with have a chance to compare with the previous seasons performance.
  • With user friendly interfaces and SQL based infrastructure, Deloitte’s solution ensures a detailed planning, at store, product group and week level.
  • In addition to merchandise planning module, initial allocation planning and purchasing plan modules are provided by Deloitte’s solution. 

Pre-Season Planning Tool

  • Deloitte developed a Qlikview based tool that helps the users to have strategic decisions effectively. Tool combines the Competitive Intelligence,  fashion & lifestyle maps, decision trees, product architecture, collection architecture with previous seasons’ collection structures and strategic insights.

─        With Competitive Intelligence survey competition data are collected and imported into database, then using competitive intelligence modules competitors price levels, product mix(product breadth and depth), product display data are analyzed

─        With Decision Tree Modules determining number of option, average ticket price, number of unit per option, average unit costs, initial mark-up and markdown loss are determined at high level.

─        Merchandise Architecture Module includes channel based product breadth and depth, average ticket price, realized price, revenue, profitability, cost, initial mark-up, mark down loss for new season at financial and operational level.

─        Collections are distribute and analyzed via Fashion & Lifestyle Map and Fashion Price Map.

─        Options are assigned to the collections with number of option, number of unit per options, initial mark-up, revenue, cost, gross margin and display information. 

Collection Planning

  • Deloitte developed a tool that integrates store transfer, allocation and replenishment at the same platform.
  • Tool, minimizes the inefficiencies and merchandising and inventory management and improves margin significantly due to advanced analytical modeling
  • Tool can easily integrated to the IT systems of clients and it aims to minimize the inefficiencies with iterative algorithms and CPLEX optimization tools.

─         Store Transfer Optimization: Because of inaccuracies in planning and uncertainties, some imbalances occur among the inventory levels of stores which causes lost sales. Deloitte’s solution comes the consolidated experience in analytics and retail management, aims to prevent the lost  sales and also decrease the operational cost caused by transfer.

─         Replenishment Optimization: It is clearly important to replenish the inventory of stores which decreased by the sales during the season to prevent the potential lost sales. Replenishment  is a complicated  problem that focuses on the store capacities, warehouse inventory and sale performance of stores are the key parameters of the replenishment optimization. Deloitte’s replenishment optimization solution aims to maximize the total sales of store with distributing the existing inventory level.

─         Allocation Optimization: Because of drastic decrease of inventory level at stores, retail companies may need to change positioning rules for products. With combining the new rules, existing inventory levels, sale potentials, Deloitte’s solution minimizes the lost sales.

In Season Planning Optimization

  • Attractive  marketing locations are identified by utilizing  geospatial and visual analytics  methods that consider macroeconomic data, competitor store information,  demographic factors and other industry-specific variables.
  • The study aides with the assessment of current store performance as well as with the selection of potential new store locations.

Target Market and Location Analysis through Geospatial Analytics

  • Deloitte integrates CAST optimization tool with advanced analytical modelling in order to optimize supply chain operations
  • Supply chain costs are reduced by answering critical questions such as "where should we produce" and "how should we distribute" and  by taking into account design requirements as well as production and distribution restrictions.

Supply Chain Optimization

  • Sales and profitability performance, portfolio analysis, store features and competitive intelligence are statistically analyzed to store the clusters to improve channel efficiencies.
  • Integration with Data Envelopment Analysis, cluster and store specific action plans are developed to improve the performance.

Store Clustering

  • Large and complex data is visualized in a user friendly way to enhance the analysis capabilities and support the decision taking system via transparent, to the point and advanced insights
  • Qlickview and Tableau tools are utilized to gather, store, integrate, visualize and analyze the data from multiple sources  

Data Visualization