BDB Customer Analytics: Comprehensive study of Modern Consumers

by Nikita Agrawal

Companies in nearly every industry are feeling the heat from more observant and often less loyal consumers. Therefore, the current businesses should have a careful and comprehensive understanding of their customers to get a hold of them, grow them, and sustain them.

Customer Analytics gives valuable insights to understand the customer’s purchase & usage patterns, demographic distribution & profitability. Organizations based on customer analysis insights can segment customers, understand their behavior, create loyalty programs, decide the best pricing, and optimize cost.

Benefits of Customer Analytics for an Organization
  1. Deliver the right message more effectively by Customer Segmentation
  2. Decrease attrition rate by accurately predicting the customers who are most likely to churn
  3. Develop proactive strategies to retain valuable customers
  4. Contact the right customers at the right time with right offers
  5. Reduce Campaign costs by targeting customers who are more likely to respond
How does BDB Decision Platform help to Achieve Customer Analytics?
  1. BDB has developed a Data Pipeline framework which can read Data from Real-time, Near Real-time, Batch(scheduled), Process from IOT, Websites, Third Party APIs, Data Feeds, etc.
  2. BDB Platform can handle a large amount of data & cleanse it through Data Quality procedures.
  3. BDB owns a dedicated Data Science team which has established effective algorithms for Customer Analytics, also have off the shelf AI-based Algorithms to analyze prominent Sentiments, Image, and Video Analytics.
  4. Our teams can provide seamless Visualization through the best of the breed data visualization tools

Customer Segmentation

As your business grows, segmenting your customers can significantly improve your marketing performance, making campaigns more relevant to most of your customers ultimately, increasing response rates and sales.

Recency -Frequency – Monetary (RFM)- RFM Analysis is a proven direct marketing model for behavior-based customer segmentation. RFM helps to group customers based on their transaction history – it segregates the customers based on how recently, how often, and how much they paid for their purchases.

Customer Churn

Customer Churning refers to regaining the customer who has ceased his or her relationship with the company. Businesses typically treat a customer as churned once an amount of time has elapsed since the customer’s last interaction. The full cost of customer churn includes both lost revenue and the marketing expenses involved with replacing those customers with new ones.

The ability to predict that a specific customer is at high risk of churning, while there is still time to do something about it, represents a considerable additional potential revenue source for every business. Besides the direct loss of revenue that results from a customer abandoning the business, the costs of initially acquiring that customer may not have already been covered by the customer’s spending to date. Moreover, it is always difficult and expensive to acquire a new customer than it is to retain a current paying customer.

Customer Lifetime Value

In Marketing, Customer Lifetime Value is a prediction of net profit attributed to the entire future relationship with a customer. It estimates a customer’s monetary worth to business after factoring in the value of a relationship with a customer over time.

CLV helps you make confident business decisions about sales, marketing, product and customer support.

  1. Marketing - How much money a company should spend on acquiring new customers?
  2. Product - How can I offer products and services tailored for my best customers?
  3. Customer Support - How much should I spend to service and retain a customer? How much repeat business a company can expect from certain consumers?
  4. Sales - What types of customers should sales representative approach and spend the most time on trying to acquire?

Sentiment Analysis

Sentiment Analysis is basically Opinion Mining. The process of computationally identifying and categorizing opinions expressed in a piece of text, primarily to determine whether the writer's attitude towards a topic, product, etc. is positive, negative, or neutral.

It is important to classify incoming customer conversation about a brand based on 2 factors:

  1. Key aspects of a brand that customer care.
  2. 'Users' underlying intentions and reactions concerning those aspects.

These concepts when used in combination, become a vital tool for analyzing millions of brand conversations with human-level accuracy.

Description: The workflow takes tweets data as input and Classifies these tweets as positive, negative, or neutral based on LSTM based NN.

Algorithm Used LSTM Neural Network

Brand Sentiment Analysis

Customer Buying Patterns & Behavior

Buying pattern refers to the typical way in which consumers buy goods or avail services- encompassing frequency, quantity, duration, timing, etc.

Customers have different agendas and different concerns as that of a salesperson.

  1. Market Basket Analysis – It is a theory that if you buy a specific group of items, you are more (or less) likely to buy another group of items.
  2. Conjoint Analysis - Choice Based Survey Data, it gives various combinations of attributes as choices and people choose out of these options.

Algorithm Used Multinomial Logistic Regression

Demand Forecasting

Most of the business decisions of an organization are made under the conditions of risk and uncertainty.

Demand forecasting is a systematic process that involves anticipating the demand for the product and services of an organization in the future under a set of uncontrollable and competitive forces.

Market Share Analysis

Considering the competition between brands in the market, it is often of interest to model market-shares.

  1. Price Elasticity - Using historical variations in price and purchase volumes to discover the optimal price to charge for different audiences at different times, optimizing profit and return on investment.
  2. Brand Shifting Analysis (Cross Elasticity) - What is the source of a brand’s growth or decline? Which brands are being cannibalized?
    1. New/Lost category buyers
    2. Increased/Decreased category buying
    3. Brand Switching
  3. Overlap Analysis - Overlap analysis provides a measure of the level of duplication within a group of products. Also helps in identifying solus buyers (brand buyers who exclusively buy that variant) and hence the walk rate.

Campaign Analytics

  1. BDB solution helps you track your campaign’s performance on Facebook, Google Ads, LinkedIn, Twitter and MailChimp.
  2. Compare your campaigns across different platforms, get to know which platform proves to be the best for what type of campaigns.
  3. How relevant your ads are to your target audience?
  4. What is the best time to post your Ad, have a grasp of Return on Advertising Spend (ROAS) and (ROI)?
  5. Visualize how your campaigns are bringing visits, clicks, and conversions to your site.

Customer analytics is among the most compelling enablers companies should have for translating those signals which they are unable to convert into useful insights about their customers. BDB Customer Analytics helps to deliver better customer insights, in a format that makes it easy to understand and act on them.