Creating a Better Customer Experience and Achieving a Higher Return from Data Analysis
Usually online or offline advertising is designed for attracting more customers to visit online shops, brick-and-mortar shops, and drive up traffic. However, this approach is not necessarily aligned with the customer-centric thoughts, which leads enterprises to waste a lot of money and energy on inefficient marketing resources.
Finally, you have customers coming through your front door, but the real challenge of generating sales and closing the deal has just begun.
Etu Recommender has the answers for the above business-wise agendas that are waiting to be solved. Through an analysis of collective intelligence, we are able to enable precisely personalized recommended solutions.
“One-to-One Commerce” is not just a slogan. Etu Recommender has allowed business users to discover the specific preferences, tastes, and needs of their customers without intruding upon customers about their needs. Moreover, it will recommend matches for the customers’ most wanted goods based on their preferences and increase the market efficiency in sales revenues and volume of goods.
Figure 1. The Core Concept of Etu Recommender
The analysis of an Etu Recommender consists of a transaction record, customer’s behavior, and data analysis consisting of two “groups”:
01 User-based: Intelligence analysis based on the similarities of a user’s behavior.
02 Item-based: Intelligence analysis based on the correlation of goods.
Etu Recommender uses Big Data platform to do a cross intelligence analysis based on the data of users and the information of goods in order to put out a personalized recommendation list. In other words, it uses accumulated data to find out common interests, common behaviors, common purchasing, and surfing experience of users in order to recommend the most attractive goods to users.
A recommender is utilized to realize click rates and purchasing rates generated from personalized recommendation lists.
Figure 2. Etu Recommender Collective Intelligence Analysis
The recommendation list is generated by an Etu Recommender, which serves as a virtual shopping guide. Take an e-commerce website as an example, the standard recommendation categories include:
Figure 3. Etu Recommender's recommendation list and respective data sources
After generating a recommendation list that can be integrated into different web pages such as a landing page, introduction of goods page, shopping cart list page, member page, search result pages, and/or a checkout page by various categories without changing the website style. All presented as if a real and thoughtful shopping guide has recommended customers what to buy, what should not be missed based on the collective intelligence analysis consisting of user similarities, and correlation of goods at the right moment even in different situations.
01 Discover Customers' Intentions
Understand customers' preferences , explicit and unknown tacit tendencies by intelligently analyzing the overall batch transacted data and online behavior data.
02 Remarkable Effect
Extraordinary recommendation performances can be presented on an operational dashboard. This will help increase the order conversion rate and averaged transaction amount of each order.
03 Offline and Online Integration
Both online and offline recommendations can be operated separately or can be integrated.
04 Multiple Virtual Shopping Guides
One Etu Recommender, the virtual shopping guide serves one single domain. Multiple Etu Recommenders can serve multiple online stores or multiple categories in one shopping mall.
05 Rapid Deployment
It is the End-to-End Solution, which can be implemented quickly. The deliverables include software and hardware.
06 Expansion as Growth Increases
Architecture of Cloud Lineage can easily fulfill the needs for capacity expansion and business & data growth demands.
Figure 4. Remarkable Features of Etu Recommender
The analysis of the users’ similarities to simply recommend goods or to recommend by the correlation of goods to find out the customers who love or may need these particular goods are the tasks that the Etu Recommender can complete both online and offline. The difference between the online and offline recommendation list are the delivery channels:
When an Etu Recommender applies to other online services such as e-commerce, digital media, or e-trading the recommendation list will be available through a web page or email.
Figure 5. Etu Recommender Online Application - E-Commerce
Figure 6. Online Application and Implementation of an Etu Recommender
When Etu Recommender applies to other physical trading places, such as retailing, circulation, chain stores, or department stores, the personalized recommendation list will be delivered through such channels as correlated display of goods, telemarketing, catalogue, or email.
Figure 7. Etu Recommender Offline Applications - Retailing, Chain Stores, Department Stores
Figire 8. Offline Application and Implementation of an Etu Recommender
When business demands change from online to offline or from offline to online, Etu Recommender can handle both virtual and physical integrated recommendations.
Figure 9. Online and Offline Integration Application of Etu Recommender
An Etu Recommender, through personalized recommendation realizes the core value of One-to-One Commerce. Each customer can be regarded as a segmented market. The major benefits for enterprises adopting an Etu Recommender either for online or offline applications can make an immediate impact including:
01 Increasing Purchase Conversion Rate
Complete up-selling and cross-selling to increase the sales revenue of each order and expand revenue scales.
02 Increasing Customer Loyalty
Keeping contact of personalized recommendations after order to create new trading circles and to increase repeat order rate.
03 Comprehensive Personalized Recommendation
Both online and offline creates the best and most personalized experience to increase customer satisfaction.
04 Leveraging Long-Tail Effect
The sales cycle of less popular goods can be extended by analyzing the correlation of goods and the similarities of customers.
Please check the < Etu Recommender Solution Guide > for detail.
Download: < Etu Recommender Solution Guide > (279KB)