Attain Accurate Customer Analytics
BDB has developed a Framework for Data Pipeline which can read Data from Real-time, Near Real-time, Batch(scheduled) Process from IOT, Websites, Third Party APIs, Data Feeds. BDB Platform can handle the massive amount of data & cleansing through Data Quality procedures. Our experienced Data Science team has specialized algorithms to offer accurate Customer Analytics. BDB Decision platform owns off the shelf AI-based Algorithms for Text, Voice, Sentiments, Image, and Video Analytics. BDB provides high-end visualization module with drag and drop interface to build governed dashboards and self service dashboard with AI based Search.
Customer Analytics is essential to get proper insights into customer’s buying behaviors, usage patterns, demographic distribution, and profitability. Organizations need to put their considerable time and resources to understand their customers and analyze the data generated by their interactions with customers.
In today’s digitized world, the AI-driven Data Science has become the core as it has the unlimited processing power to analyze each customer and build personalized relationships. It can segment customers, quickly understand their purchase patterns, create loyalty programs to choose the best pricing and optimize the cost.
Modern AI technologies like Voice Recognition, NLP based interactions, Image/Video Processing, Sentiment Analytics have changed the way data analytics was applied till now in the customer facing industries.
Customer segmentation is the process of dividing customers into groups based on common characteristics so companies can market to each group effectively and appropriately. A company might segment customers according to a wide range of factors.
As your business grows, segmenting your customers can significantly improve your marketing performance, making campaigns more relevant to more of your customers, ultimately increasing response rates and sales. In the long run, this benefits the company because they can use their corporate resources more effectively and make better strategic marketing decisions.
- CLV - RFM
- Hierarchical clustering and K- means
- Customer Movement Pattern
Sense of Purpose
- Increased customer retention, response rate, conversion rate & Revenue
- Identify your Best | Valuable | Big Spenders | Churn | Uncertain customers
- Which of your customers are most likely to churn?
- How many one-time customers do you have?
- Identify your loyal customers
A customer-centric metric, and a powerful base to build upon to retain valuable customers, increase revenue from less valuable customers, and improve the customer experience overall. RFM Analysis is a proven direct marketing model for behavior-based customer segmentation. It groups customers based on their transaction history - how recently, how often and how much did they buy.
Input data consists of Recency, Frequency and Monetary values for each customer. CLV has been calculated for each customer by predicting retention rate based on logistic regression and Segmentations done based on RFM
Hierarchical cluster analysis is an algorithm that groups similar objects into groups called clusters. The endpoint is a set of clusters, where each cluster is distinct and the objects within each cluster are broadly similar to each other.
K-means clustering is a type of unsupervised learning, which is used when you have unlabeled data (i.e., data without defined categories or groups). The goal of this algorithm is to find groups in the data, with the number of groups represented by the variable K.
Customer Analytics and Buying patterns
A customer behavior analysis is a qualitative and quantitative observation of how customers interact with your company. It provides insight into the different variables that influence an audience. It also gives an idea of the motives, priorities, and decision-making methods being considered during the customer's journey.
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.
- CLV – RFM
- Brand Shift Analysis
- Survival Analysis – It represents a huge additional potential revenue source for every business
- Market Basket Analysis
- Demand Forecasting
- Conjoint Analysis
- What-if Analysis
Sense of Purpose
- Effective targeting & personalization
- How much money a company should spend on acquiring new customers?
- How can I offer products and services tailored for my best customers?
- How much should I spend to service and retain a customer? How much repeat business a company can expect from certain consumers?
- Gain actionable insight to increase your brand’s competitive edge
- Formulating Production & Pricing policy
- Controlling Sales targets in different regions/areas
Survival analysis is generally defined as a set of methods for analyzing data where the outcome variable is the time until the occurrence of an event of interest. To understand length of time before an event occurs. To predict time till next event.
The input data give time period of observation and various other parameters about the customers and predicting time till churn for the customers who have not churned yet.
Demanding forecasting is the use of data and analytics to predict as precisely as possible the customer demand for a specific period. Accurate demand forecasting is important to satisfy customers, minimize inventory costs and optimize cash flow.
Market Basket Analysis is one of the key techniques used by large retailers to uncover associations between products. It works by looking for combinations of items that occur together frequently in transactions. To put it another way, it allows retailers to identify relationships between the items that people buy. It is a theory that if you buy a certain group of items, you are more (or less) likely to buy another group of items.
Interaction indices for different products is calculated which is indicative of product’s standing against competitors.
Input Data is household level data of retail buying and interactions between these products have been calculated.
Output is matrix showing interaction indices with other products in the market.
Market Share Analysis
Market share analysis is a part of market analysis and indicates how well a firm is doing in the marketplace compared to its competitors.
- Price Elasticity - Price elasticity is a measure of the responsiveness of demand or supply of a good or service to changes in price.
- Switching Analysis - Using the household buying data the preference change probability for a product is calculated
- Brand Shifting Analysis (Cross Elasticity) - What is brand’s source of growth or decline? Which brands are being cannibalized?
> New/Lost category buyers
> Increased/Decreased category buying
> Brand Switching
- 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.
Sense of Purpose
- Measure effectiveness of an effort
- Improving business strategies
- Factors to be focused
Market-share elasticity is the ratio of the relative change in a market share corresponding to a relative change in a marketing-mix variable (product, price, promotion, place). Considering the competition between brands in a market, it is often of interest to model market-shares. Thus, this type of model is widely used in marketing.
Economic Elasticity based on the Market Share of the Customer’s Product was determined along with their Competitor Products using MCI & MNL Models.
Improved the Accuracy of the Elasticity by including the Seasonality, Revenue, Promo Price, Promo Sales into the Model.
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.
The probability of switching between different products is calculated based on the household level retail data. This helps in identifying the competition for each product.
An overlap analysis can be carried out to determine whether there is extensive overlap between the two products.
Input Data is the household level retail data and the percentage of buyers exclusively buying that product is given as output.
Survey Based Analysis
Customer Experience improvement efforts rely heavily on the Customer Feedback to help organizations know Where and How to do the improvements. Majorly, there are three categories
- Customer Loyalty
- Customer satisfaction
- Relative Performance
Sense of Purpose
- Improving Customer Experience.
- Gain actionable insight to increase your brand’s competitive edge.
- Formulating Production & Pricing policy.
- Business Growth.
- Root causes of its detractors’ experiences & the factors of the success that turned simple customers into promoters.
Conjoint analysis is a survey-based statistical technique used in market research that helps determine how people value different attributes (feature, function, benefits) that make up an individual product or service.
Input data Choice Based Survey Data (for computers in this case), it gives various combinations of attributes as choices and people choose out of these options.
- Focus on Your Best and Valuable Customers through Loyalty Programs so that they don’t churn.
- Give discounts to customers on their frequent purchase.
- Attract first time customers through benefits of Loyalty Programs to move them towards Best or Valuable Customers.
- Monitor Customer Reactions through Promotions, Loyalty Programs and Campaign Management.
- Millennials are interested in paid Loyalty Program Tie ups.
- Bring in new Loyalty Currencies and its impact – like Amazon GO, Paytm, etc.
- 37% of customers are willing to pay for access to enhanced benefits. Early technology adopters, Gen Z and millennials are driving this trend, with 69%, 47% and 46% respectively.
Sense of Purpose
- Most Loyalty Programs results into Higher Sales.
- Profit per bill cut may reduce but it brings long term customers.
- In the above chart, we have shown how for a customer’s sales /profit through Promotion has increased after certain amount of time and then it sustained for years.
- It also helps in finding out Customer Preference in advance.
Social Media Analytics
Social media analytics is the practice of gathering data from social media websites and analyzing that data to make business decisions. The most common use of social media analytics is to mine customer sentiment to support marketing and customer service activities.
Social media is a good medium to understand real-time consumer choices, intentions and sentiments. The most prevalent application of social media analytics is to get to know the customer base to help better target customer service and marketing.
There is a tremendous amount of information on social media today. In decades past, enterprises paid market research companies to poll consumers and conduct focus groups to get the kind of information that consumers now willingly post to public social media platforms.
- Campaign Analytics
- Sentiment Analysis
Sense of Purpose
- Optimize market Campaigns
- Understanding customer attitude and reacting accordingly
- Budget & Resource Allocation
- Target Customers
- Which digital platform is proving to be best for your customers?
We believe it is important to classify incoming customer conversation about a brand based on 2 factors, Key aspects of a brand that customer care about., Users underlying intentions and reactions concerning those aspects. These concepts when used in combination, becomes a very important tool for analyzing millions of brand identity with human level accuracy.
The workflow takes tweets data as input and classifies these tweets as positive, negative and neutral based on LSTM based NN
Sense of Purpose
- Real – time Analysis.
- The overall customer experience of your users can be revealed quickly with sentiment analysis, but it can get far more granular too.
- Understanding customer attitude and reacting accordingly.
In todays era, tracking your money spent along with the returns that the business gets out of the campaigns run on social media has become a need for every organization.
With our Campaign Analytics Solution, compare campaigns carried out on different platforms which will cater to the problem – Where & How much to invest?
- BDB solution will help you track your campaign’s performance on Facebook, Google Ads, LinkedIn, Twitter, Mailchimp and others.
- Compare your campaigns across different platforms, get to know which platform proves to be the best for what type of campaigns.
- How relevant your ads are to your target audience?
- What is the best time to post your Ad, have a grasp of Return on Advertising Spend (ROAS) and (ROI)?
- Visualize how your campaigns are bringing visits, clicks, and conversions to your site.
Sense of Purpose
- Multichannel data collection through data pipeline
- Identify target market
- Brand Awareness
- Optimize marketing Campaigns – Budget Allocation
- Track User Behaviour / Referral Links
- Lead Generation
Image & Video Analytics
Image Analytics is a logical analysis of information found in image data using digital image processing techniques.
Video Analytics is the capability of automatically analyzing video to detect and determine events.
- Brand Identification
- Video Classification
Sense of Purpose
- Customers real time face emotions can be analyzed to judge their satisfaction level.
- Total time duration of a brand can be detected during a sports match or any other campaign to measure ROI
- Crowd Management
To Identify the Brand Logo in the image from the football clip.
It was successfully implemented with > (95-96)%
- 360° customer views & reports
- Data Enrichment & Integration - Using data enrichment will give the team actionable and accurate information. This would result in reps spending less time researching and more time selling.
- Marketing Automation – Sales and Marketing teams play different roles in the quest to achieve a shared goal. Therefore, Marketing Automation connects their efforts to boost success. The is a segment of Customer Relationship Management (CRM), and is typically used by marketing departments to remove repetitive tasks from staff workflows and increase overall marketing efficiency. Marketing Automation tracks the Customer Journey.
Sense of Purpose
- Simplify the process of analyzing information and extracting insights to save time and increase productivity
- Streamline operations
- Improved Decision Making
- Improved Customer Experience
Its primary purpose is to indicate the level and direction of future business activity so that all teams and functions in a company have time to respond to changes.
Input data contains daily sales information with exogenous variables (e.g. Temperature) and sales forecasting has been done by using SARIMAX model.