Price optimization

Retail optimization challenges and opportunities

Retailers face mounting challenges as they work to maintain their market position while maximizing profitability. Pricing has long been one of the key levers available to retailers to drive sales, attract new customers, retain existing customers, and increase market share. However, over the last decade, it has gained even more significance as the rise of ecommerce and omnichannel shopping has made it easier than ever for consumers to buy—and compare prices across multiple retailers before they do.

Inaccurate, fragmented, or, sometimes, too much information can make it challenging for retailers to make the right pricing decisions. And while strategic pricing can be a key way retailers can differentiate themselves from their competitors, uninformed pricing decisions can have a significant negative impact on revenue, profitability, and customer satisfaction. Given the thin margins most retailers work with, determining the best price to maximize a product’s sales, profitability, and market share is critical. However, due to data challenges, many retailers must make pricing decisions without understanding the demand or the impact price changes will have on sales and margin, and they must make tens of thousands of these underinformed pricing decisions across their assortment.

The ability to bring diverse datasets together and apply advanced analytics and machine learning at scale enables retailers to broaden their pricing strategies to include competitive pricing, psychological pricing, promotional pricing, price bundling, and increasingly dynamic pricing; identify the correct pricing strategy (or combination of strategies); and optimize their pricing. They can then push the right products and services at the right price to the right customer through the appropriate channel at the appropriate time.

Simplify retail planning with advanced analytics and machine learning

Let’s look at how Oracle Data Platform is built to help retailers identify the correct pricing for individual products, optimize that pricing throughout the product lifecycle, and understand the price-volume-market-time relationship.

This image shows how Oracle Data Platform for retail can be used to support price optimization and help retailers maintain market position while maximizing profitability. The platform includes the following five pillars:

1. 1. Data Sources, Discovery
2. 2. Ingest, Transform
3. 3. Persist, Curate, Create
4. 4. Analyze, Learn, Predict
5. 5. Measure, Act

The Data Sources, Discovery pillar includes three categories of data.

1. 1. Business record (first-party) data comprises sales transactions, and customer, supplier, inventory, POS system, revenue, and margin data.
2. 2. Application data comes from ERP, SCM, CX, WMS, Fusion SaaS, NetSuite, Oracle E-Business Suite, PeopleSoft, JD Edwards, SAP, Salesforce, and Workday applications.
3. 3. Third-party data includes competitor data, data from Oracle Advertising, economic data, and social data.

The Ingest, Transform pillar comprises three capabilities.

1. 1. Batch ingestion uses OCI Data Integration, Oracle Data Integrator, and DB tools.
2. 2. Bulk transfer uses OCI FastConnect, OCI Data Transfer, MFT, and OCI CLI.
3. 3. Change data capture uses OCI GoldenGate.

All three capabilities connect unidirectionally into the cloud storage/data lake within the Persist, Curate, Create pillar.

The Persist, Curate, Create pillar comprises four capabilities.

1. 1. The serving data store uses Oracle Autonomous Data Warehouse.
2. 2. Cloud storage/data lake uses OCI Object Storage.
3. 3. Batch processing uses OCI Data Flow.
4. 4. Governance uses OCI Data Catalog.

These capabilities are connected within the pillar. Cloud storage/data lake is unidirectionally connected to the serving data store; it is also bidirectionally connected to batch processing.

One capability connects into the Analyze, Learn, Predict pillar: The serving data store connects to both the analytics and visualization capability and machine learning capability.

The Analyze, Learn, Predict pillar comprises two capabilities.

1. 1. Analytics and visualization uses Oracle Analytics Cloud, GraphStudio, and ISVs.
2. 2. Machine learning uses OCI Data Science, Oracle ML, and Oracle ML Notebooks.

The Measure, Act pillar comprises three consumers: dashboard and reports, applications, and machine learning models.

Dashboard and Reports comprises Sales, Performance, Inventory Levels, and Competitor Pricing.

Applications comprises Price Elasticity Models, and Pricing Rules.

Machine Learning Models comprises Customer Behavior Patterns, and Market Specific Pricing.

The three central pillars—Ingest, Transform; Persist, Curate, Create; and Analyze, Learn, Predict—are supported by infrastructure, network, security, and IAM.

There are three main ways to inject data into an architecture to enable retailers to optimize prices.

• To start our process, we need to understand our overall inventory position to ensure products aren’t overstocked or understocked. We can use this data to decide whether to adjust prices to either move inventory or avoid a stockout. To do so, we use OCI GoldenGate to enable change data capture ingestion of near real-time warehouse inventory data from operational databases for all or a subset of product lines.
• We can now add datasets relevant to customers (such as their preferences, behaviors, and purchasing patterns), costs (such as the production cost and sales cost), and retail demand (such as point-of-sale information). To anticipate changes in customer behavior, retailers also need to understand market conditions (such as supply and demand), economic trends, and consumer sentiment. Retailers also need to monitor their competitors' prices and promotions to ensure they’re staying competitive. These datasets often comprise large volumes of often on-premises data, and in most cases, batch ingestion is typically most efficient. For our point-of-sale data, we will use Oracle Data Integrator to ingest the data on a four-hour cycle.
• Bulk ingestion can be used for the initial data load or to migrate data from on-premises data stores.

Data persistence and processing is built on three components.

• Ingested raw data is stored in cloud storage. We will use OCI Data Flow for the batch processing of this now persisted data, including stock levels, geo-mapping data, and product reference data. These processed datasets are returned to cloud storage for onward persistence, curation, and analysis and ultimately for loading in optimized form to the serving data store.
• We have now created processed datasets that are ready to be persisted in optimized relational form for curation and query performance in the serving data store provided by Oracle Autonomous Data Warehouse. This will enable us to identify and return the products by price, demand profile, inventory level, and location.

The ability to analyze, learn, and predict is built on two technologies.

• Analytics and visualization services deliver the following capabilities:
  • Descriptive analytics (describes current trends with histograms and charts) supports the development of rule-based pricing algorithms that use predefined rules to adjust prices based on specific criteria, such as sales performance, inventory levels, or competitor pricing. For example, a retailer may set a rule to decrease the price of a product by 10% if it has been in stock for more than 30 days.
  • Predictive analytics (predicts future events, identifies trends, and determines the probability of uncertain outcomes) uses historical sales data to identify correlations between price and demand. Retailers can use this analysis to predict how changes in price will affect demand and adjust prices accordingly. Additionally, predictive analytics can provide price elasticity models, which use statistical models to measure how sensitive demand is to changes in price. Retailers can use this analysis to identify the optimal price points to maximize sales and profitability.
  • Prescriptive analytics (proposes suitable actions to support optimal decision-making) can be used for dynamic pricing. This algorithm uses real-time data, such as inventory levels, competitor pricing, and customer behavior, to adjust prices in real time. Retailers can use this to respond to market changes quickly and optimize prices for maximum profitability.
• Alongside the use of advanced analytics, machine learning models are developed, trained, and deployed. These models use artificial intelligence to analyze large amounts of data and identify patterns and trends that can be used to optimize prices. Retailers can use machine learning algorithms to predict customer behavior, identify pricing opportunities, and optimize prices across multiple products and markets.
• Our curated, tested, and high-quality data and models can have governance rules and policies applied and can be exposed as a "data product" (API) within a data mesh architecture for distribution across the retail organization.

Increase profitability with a retail data platform

The right pricing strategies can increase revenue, profitability, market share, and customer satisfaction, but to develop them, retailers require real-time access to inventory levels, orders, demand, current pricing and promotions, and 360-degree customer views. By using a data platform that integrates data from multiple sources and supports advanced analytics, retailers can easily tailor their pricing strategies at the product level while aligning prices with corporate and category goals across all selling channels. This flexibility allows retailers to propose regular prices based on their target margins, competitive price alignment, or their preferred pricing relationship between different markets and maximize the value of their promotion and markdown strategies—all while providing a superior omnichannel customer journey by ensuring individual consumers experience pricing consistency at every touchpoint.