How to install TensorFlow on Anaconda – Easiest method to follow by

Topbullets.comTensorFlow is mainly developed by Google and released under open source license. We can easily access Tensorflow in Python to create Deep Learning models. I had to use Keras library for Recurrent Neural Networks and found that I need to install Tensorflow to use Keras. I really found the process very tough. For people like me who has very less knowledge about Python or pip or conda, it was a nightmare. Finally, I could solve the issue and installed the package successfully but had to read hundreds of articles and followed more than 10-15 methods, installed Anaconda more than 7-10 times to get the right version. As I have faced all these issues and installed it successfully, I thought of writing about it. Also, one of my dearest friends keeps me pushing to write a blog at least once a week so hopefully this will help me. Though there are hundreds of articles and there is very less chance that my blog would appear in Google search like other articles, but it is worth sharing and writing. Continue reading

How to Create Cascading Filters in R Shiny Dashboard by

Topbullets.comIn Data Science visualization is a powerful tool. You can’t sell a concept but a product. Data analytics is science but presenting them through different graphs and charts is an art. We have many ways to present the numbers and a lot of software which make our life easy. Few of them which I have tried are Tableau, R Shiny, D3, QlikView and VBA Dashboard. Every tool has its own advantages and properties. Currently, I am working on R Shiny dashboard which is so beautiful and easy to learn. I would really encourage you to learn R Shiny if you do coding in R. It has a lot of in-built packages which can easily be deployed. Today let’s work on cascading filters one of the most important kinds of filters. Every other filter is connected to the predecessor filter. Continue reading

Assumptions of Linear Regression by

Topbullets.comIn my previous post I mentioned some techniques one should know if they want to pursue a career in Data Analytics. In those lines, I would like to discuss a few topics in detail. This blog post is on Linear Regression, that would serve as an easy starter and then I would slowly move to other techniques. Linear regression is the most used technique in data science. Generally, when we say linear regression we refer to additive model which means dependent variable will be a function of all independent variables and there would linear and additive relationships. Continue reading

How to launch your career in data analytics after college graduation?

Topbullets.comRecently I started answering on Quora. It caught my attention that people pursue a lot of interest in the Analytics domain. Being a blogger, it is my utmost responsibility to cater to the educational needs of the masses, hence this blog will be related to basics of analytics and where to learn, some misconceptions around analytics and career scope. I have 3 years of experience in the Analytics industry, and I would leave this discretion to the readers to decide if they find my blog useful.
Continue reading

Personalization Software Demo – A Tool in Online Marketing

Personalization: When we personalize our product or services to provide more value to customers, it’s called personalization.
Personalization has following important features.

  • Improve retention and lifetime customer value by personalizing the entire customer experience.
    –Boost Average Order Value
    –Increase Conversions
    –Improve Customer Loyalty 
with the Resonance Omnichannel Personalization Platform
  • Specially used in eCommerce
  • Convert shoppers with optimized product recommendations, content, and promotional offers
  • Engage visitors with personalized landing pages tailored in real-time to the context of their visit
  • Reduce costs and IT workload with less time spent on manual merchandising
  • Analyze with in depth, real-time reports and analytics

To analyze personalization software, I have taken Certona Software. Certona is providing its personalization platform which is called “Resonance Omni channel Personalization Platform”.
About ‘Certona’

    • Deliver Personalized Customer Experiences
    • More than 400 top ecommerce sites
    • Software helped to generate over US $23 billion in 2012.
    • Apparel, Specialty, Office Supplies, Luggage, Skincare
    • Internet Retailer’s Top 500 Guide : 2009 – 2013

This software provides few features that are listed below.
Acquire more customers with personalized marketing campaigns that drive more traffic
Engage visitors immediately with personalized landing pages tailored in real-time to the context of their visit
Convert shoppers with optimized product recommendations, content, and promotional offers
Re-market to customers with personalized transactional emails and personalized opt-in alert marketing

First it helps us to ‘Acquire’ customers, to bring customers from various channels to our websites. Then it engages them to visit different products, promotional offers and discounted products. Then keep suggesting customers to visit other substitute products or complement products as well. Then they influence the customers to purchase from the websites and after purchasing they always send recommendation and suggestion so that we can retain our customers.
How it works.
When someone visits our website, it recognize it’s like and dislike with 3-4 clicks which is current session and take data from previous history as well, which is saved in browsers cache and customer’s purchasing history, cart history and wish lists. Certona combine all these data and apply an algorithm, called ‘Multi Algorithm Optimization’. It applies best Business policy and promotional offers and show suggestion on web page or sends message to mobile or mail to email id.
Below image is detailed explanation of what certona is doing when a customer is logged in.

personalization software - deepesh

Below image shows how it study the traffic. Certona keeps tracking the real time sales and it find that sales between 7 PM – 8 PM are much higher than rest of the day. The reason is that most of the persons who are having jobs, return home and after getting relaxed they start purchasing.

personalization software - deepesh

The above image has been taken from Certona white paper. It shows the conversation rate with recommendation and without recommendation. The conversation rate in 2011 with recommendation is 7.71 % while without recommendation it was only 2.63%. So Certona helps us to convert and retain customers.
Few examples of Certona Application are listed below.
1. Sending Mail with recommendation (indiashopping)
2. Sending Mail with different promotional activity (
3. Customize browsing (
4. Trending page – Auto refresh (

Certona different product and services:
Certona Recommendations™ – Real-time personalization for eCommerce websites
Certona Mobile™ – Real-time personalization for mCommerce, applications and tablets.
Certona Email™ – personalization of transactional emails and marketing campaigns
Certona Remarketing™ – timely follow up emails to cart & browser

Copyright © 2013 ·All Rights Reserved · Republishing or copying this article or any part of this without giving reference would come under WordPress Copyright Act.

If you liked this article, please rate and comment. Thank You!


Deepesh Singh