Data analyst certification Archives - Page 10 of 12 - DexLab Analytics | Big Data Hadoop SAS R Analytics Predictive Modeling & Excel VBA

Curiosity is Vital: How Machine Inquisitiveness Improves the Ability to Perform Smartly

Posted on June 2, 2017May 23, 2020 by Dexlab

What happens when a computer algorithm merges with a form of artificial curiosity – to solve precarious problems?

Meticulous researchers at the University of California, Berkeley framed an “intrinsic curiosity model” to make their learning algorithm function even when there is a lack of strong feedback signal. The pioneering model developed by this team visions the AI software controlling a virtual agent in video games in pursuit of maximising its understanding of its environment and related aspects affecting that environment. Previously, there have been numerous attempts to render AI agents’ curiosity, but this time the trick is simpler and rewarding.

The shortcomings of robust machine learning techniques can be solved with this mighty trick, and it could help us in making machines better at solving obscure real world problems.

Pulkit Agrawal, a PhD student at UC Berkeley, who pulled off the research with colleagues said, “Rewards in the real world are very sparse. Babies do all these random experiments, and you can think of that as a kind of curiosity. They are learning some sort of skills.”

Also read: Data Science – then and now!

Like several potent machine learning techniques rolled out in the past decade, Reinforcement Learning has brought in a phenomenal change in the way machine accomplish their things. It has been an intrinsic part of AlphaGo, a poster child of DeepMind; it helped playing and winning the complex board game GO with incredible skill and wit. As a result, the technique is now implemented to imbue machines with striking skills that might be impossible to code manually.

However, Reinforcement Learning comes with its own limitations. Agrawal pointed that sometimes it demands a huge amount of training in order to grasp a task, and the procedure can become troublesome, especially when the feedback is not immediately available. To simplify, the process doesn’t work for computer games where the advantages of specified behaviours is not just obvious. Hence, we call for curiosity!

Also read: After Chess, Draughts and Backgammon, How Google’s AlphaGo Win at Go

For quite some time now, a lot of research activity is going around on artificial curiosity. Pierre-Yves Oudeyer, a research director at the French Institute for Research in Computer Science and Automation, said, “What is very exciting right now is that these ideas, which were very much viewed as ‘exotic’ by both mainstream AI and neuroscience researchers, are now becoming a major topic in both AI and neuroscience,”. The best thing to watch now is how the UC Berkeley team is going to run it on robots that implement Reinforcement Learning to learn abstract stuffs. In context to above, Agrawal noted robots waste a nifty amount of time in fulfilling erratic gestures, but when properly equipped with innate curiosity, the same robot would quickly explore its environment and establish relationships with nearby objects.

Also read: CRACKING A WHIP ON BLACK MONEY HOARDERS WITH DATA ANALYTICS

In support of the UC Berkeley team, Brenden Lake, a research scientist at New York University who lives by framing computational models of human cognitive capabilities said the work seemed promising. Developing machines to think like humans is an impressive and important step in the machine-building world. He added, “It’s very impressive that by using only curiosity-driven learning, the agents in a game can now learn to navigate through levels.”

To learn more about the boons of artificial intelligence, and what new realms, it’s traversing across, follow us on DexLab Analytics. We are a leading Online Data Science Certification provider, excelling on online certificate course in credit analysis. Visit our site to enroll for high-end data analytics courses!

Interested in a career in Data Analyst?
To learn more about Data Analyst with Advanced excel course – Enrol Now.
To learn more about Data Analyst with R Course – Enrol Now.
To learn more about Big Data Course – Enrol Now.
To learn more about Machine Learning Using Python and Spark – Enrol Now.
To learn more about Data Analyst with SAS Course – Enrol Now.
To learn more about Data Analyst with Apache Spark Course – Enrol Now.
To learn more about Data Analyst with Market Risk Analytics and Modelling Course – Enrol Now.

After Chess, Draughts and Backgammon, How Google’s AlphaGo Win at Go

Posted on May 15, 2017October 10, 2018 by Dexlab

After Chess, Draughts and Backgammon, How Google’s AlphaGo Win at Go

Two decades ago, if someone asked me to write a computer program that played tic-tac-toe, I would have failed horribly. Now being an accomplished computer programmer, I know the desirable tricks to solve tic-tac-toe with the help of “Minimax Algorithm”, and what it takes is just about an hour to jot down the program. No doubt, my coding skills have evolved over the period of time, but also computer science technology has reached unattainable heights.

Computers paved the ways for a startled innovation. When in 1997, IBM introduced a chess-playing computer, known as Deep Blue, which eventually beat world-renowned Grandmaster Garry Kasparov in a six-game match, people remained in awe for years. Following the trend, in 2016, Google’s London-based AI Company, DeepMind launched AlphaGo – and it mastered over the ancient board game Go. Computers have outplayed the best human players in the games of chess, draughts and backgammon, now it’s time for Go.

Also read: Infographic: How Big Data Analytics Can Help To Boost Company Sales?

The technology goes on thriving, beating humans at games. In late May, AlphaGo is all set to take on its human rival Ke Jie, the best player in the world during the Future of Go Summit in Wuzhen, China. Games, which solely relied on human intelligence, wit, intuition, discern is now excelled by the AI, which is powered by improved engineering and computer superiority.

Also read: Top Databases of 2017 to Watch Out For

Don’t you think this is great! Where AI is driving our cars, looking for ways to cure deadly cancer and helping us in everyday work, winning at Go takes AI a step ahead. It not only makes the games more fun and exciting, but endlessly enjoyable.

The strategy explained

In the eastern part of the world, notably in China, Japan and South Korea, Go is extremely popular and many celebrities indulge in it. The game developers showed interest for long in the complexity of this game. However, the rules are simple – the main objective is to secure the maximum territories by placing and capturing black and white stones on a 19×19 grid.

Also read: Shadowing a Data Architect for a Day!

Chess is less complicated than Go; in the latter, the chances of recognising wins and losses is relatively tougher, as stones possess equal values, and ensures understated impacts throughout the board. To play Go, AlphaGo program implemented deep learning in neural networks – a brain-stimulated program. The connections formed here runs in-between layers of simulated neurons, further strengthened by examples and experiences. Firstly, it analysed 30 million positions from expert games, while gaining abstract information about the state of play from the board data, just like other programmes that classify images from pixels. After all this, finally it played against itself over 50 computers to improve its performance, with each iteration and this came to be known as reinforcement learning.

The round of applause

“AlphaGo plays in a human way”, says Fan – DeepMind’s program AlphaGo beat Fan Hui, the European Go champion. He further added, “If no one told me, maybe I would think the player was a little strange, but a very strong player, a real person.” “The program seems to have developed a conservative (rather than aggressive) style”, adds Toby Manning, a veteran Go player and a referee.

You can now get a superior quality Data Science Certification from the experts in Delhi and Gurgaon. Tune into DexLab Analytics for regular updates on business analytics certification.

Interested in a career in Data Analyst?
To learn more about Data Analyst with Advanced excel course – Enrol Now.
To learn more about Data Analyst with R Course – Enrol Now.
To learn more about Big Data Course – Enrol Now.
To learn more about Machine Learning Using Python and Spark – Enrol Now.
To learn more about Data Analyst with SAS Course – Enrol Now.
To learn more about Data Analyst with Apache Spark Course – Enrol Now.
To learn more about Data Analyst with Market Risk Analytics and Modelling Course – Enrol Now.

Demystifying Tableau Jargons: Interact With Data like Never Before

Posted on May 1, 2017June 6, 2018 by Dexlab

Businesses are flourishing. Managerial data are in abundance. The need for efficient BI softwares is at the pinnacle. Structured BI softwares are nimble and up to the minute. Tableau is one such BI tool, which is not only simple and comprehensible, but also extremely purposeful, enough to fulfil high-end professional commitments. It works just the way you want it to, instruct it in a particular way and wait for the results, without compromising the security of various confidential data.</span

Here in this FAQ blog, we have pulled out some of the top of the line frequently asked queries, regarding Tableau and R Programming. Both are highly functional, user friendly and efficient. Scroll down to grasp the basics and decode the fundamentals of Tableau.

Also read: Most Commonly Asked Tableau Interview Questions

What is Tableau?

Tableau is one of the finest data visualization tools that empower the enterprises to represent the data in the most flawless and explicit manner. It has proved its worth by being at par with its dominant predecessors, who analysed data visually and ruled the market for long.

How Tableau is classified?

Tableau can be classified as follows:

Tableau Desktop
Tableau Server
Tableau Online

What makes Tableau so popular?

With superb visualizations at an affordable price, Tableau is unrivalled. It can easily connect to any database – you don’t have to plug-in and is equipped with a robust memory processing.

Also read: Power BI or Tableau? Which is Better and Why?

Can we use precompiled models, packages, etc. with Tableau and R?

The answer is YES. If you can do it with R, you can easily incorporate it with Tableau. It includes any parallel computing modules, packages, libraries and statistical packages. It also involves commercialized versions of R, including Revolution Analytics.

Also read: How to Connect Oracle BI Server with Tableau

While you integrate Tableau and R, what is the best measure to debug R scripts or discover errors?

This is a vital question. There are mainly two ways. The first way to do this is by using ‘write.csv’ command within the studied field that calls an R script. The second one considers the use of debug version of the unparalleled executable of Rserve (Rserve_d.exe), which is ideal to print out any code that R is performing, and will be called R scripts.

Also read: Are You Trying to Ace Your Tableau Interview?

Can R be used to reshape data?

Yes, R possesses the ability of reshaping data.

Can data be transferred from a relational database to R, using Tableau?

Well, yes. Tableau can transfer data from any given source and run R scripts on that particular data set, irrespective of data type – be it relational database, flat-file, cube or unstructured.

What is Tableau Reader?

Tableau Reader is an effective tool to open the .twbx(Tableau packaged Workbook) files. However, keep in mind, it can only open files and cannot develop new connections and workbooks.

What do you mean by Tableau Public?

Tableau Public is a fantastic tool for anyone who wants to share his interesting stories on the web with others. You will gain access to data, develop interactive data visualizations and publish them on your website for others to see. And all of this, without writing a single line of code.

As parting thoughts, if you want to make something promising out of your mundane organisational data or want to make your frantic schedule of data handling and management a bit easier and enjoyable, then surely Tableau certification Gurgaon will work wonders for you! Contact us at DexLab Analytics, the pioneering data science online learning institute. We will be happy to help you.

Interested in a career in Data Analyst?
To learn more about Machine Learning Using Python and Spark – click here.
To learn more about Data Analyst with Advanced excel course – click here.
To learn more about Data Analyst with SAS Course – click here.
To learn more about Data Analyst with R Course – click here.
To learn more about Big Data Course – click here.

Drawing a Bigger Picture: FAQs about Data Analytics

Posted on April 24, 2017December 7, 2018 by Dexlab

When the whole world is going crazy about business analytics, you might be sitting in a corner and wondering what does it all mean? With so many explanations, notions run a gamut of options.

It’s TIME to be acquainted with all the imperceptible jargons of data science; let’s get things moving with these elementary FAQs.

What is data analytics?

Data analytics is all about understanding the data and implementing the derived knowledge to direct actions. It is a technical way to transform raw data into meaningful information, which makes integral decision-making easier and effective. To perform data analytics, a handful number of statistical tools and software is used and et voila, you are right on your way to success!

How will analytics help businesses grow?

The rippling effects of data analytics are evident, from the moment you introduce it in your business network. And stop rattling! The effects are largely on the positive side, letting your business unravel opportunities, which it ignored before owing to lack of accurate analytical lens. By parsing latest trends, conventions and relationships within data, analytics help predict the future tendencies of the market.

Moreover, it throws light on these following questions:

What is going on and what will happen next?
Why is it happening?
What strategy would be the best to implement?

Also read: Tigers will be safe in the hands of Big Data Analytics

How do analytics projects look like?

A conventional analytics strategy is segregated into the following 4 steps:

Research – Analysts need to identify and get through the heart of the matter to help business address issues that it is facing now or will encounter in the future.

Plan – What type of data is used? What are the sources from where the data is to be secured? How the data is prepared for implementation? What are the methods used to analyse data? Professional analysts will assess the above-mentioned questions and find relevant solutions.

Execute – This is an important step, where analysts explores and analyses data from different perspectives.

Evaluate – In this stage, analysts evaluate the strategies and execute them.

How predictive modelling is implemented through business domains?

In business analytics, there are chiefly two models, descriptive and predictive. Descriptive models explain what has already happened and what is happening now, while Predictive models decipher what would happen along with stating the underlying reason.

Also read: Data Analytics for the Big Screen

One can now solve issues related to marketing, finance, human resource, operations and any other business operations without a hitch with predictive analytics modelling. By integrating past with present data, this strategy aims to anticipate the future before it arrives.

When should I deploy analytics in business?

An Intrinsic Revelation – Analytics is not a one-time event; it is a continuous process once undertaken. No one can say when will be the right time to introduce data analytics in your business. However, most of the businesses resort to analytics in their not-up-par days, when they face problems and lags behind in devising any possible solution.

So, now that you understand the data analytics sphere and the significance attached, take up business analytics training in Delhi. From a career perspective, the field of data science is burgeoning. DexLab Analytics is a premier data science training institute, headquartered in Gurgaon. Check out our services and get one for yourself!

Interested in a career in Data Analyst?
To learn more about Data Analyst with Advanced excel course – Enrol Now.
To learn more about Data Analyst with R Course – Enrol Now.
To learn more about Big Data Course – Enrol Now.
To learn more about Machine Learning Using Python and Spark – Enrol Now.
To learn more about Data Analyst with SAS Course – Enrol Now.
To learn more about Data Analyst with Apache Spark Course – Enrol Now.
To learn more about Data Analyst with Market Risk Analytics and Modelling Course – Enrol Now.

Attributes of Effective Data Monetization Strategy

Posted on April 17, 2017May 30, 2018 by Dexlab

The saying goes – ‘necessity is the mother of all inventions’ and with the advent of globalization we have witnessed this aphorism in its sincerest form. A new wave of competition and profit generation owing to the advent of the internet, within the labyrinth of our society has led to the creation of Data at a scale previously unthinkable. To capture the essence of this huge amount of data, a new term Big Data, was coined which meant extremely large data sets, which are to be analyzed to reveal patterns that lie within.

Today, technology has become the backbone of the society and data is its vertebrae. The technological boom began and became common around year 2000; this is when data monetization became apparent.

To simplify, data monetization is the act of generating revenue by exchanging, processing and analysis of data. Processing and analyzing means extraction of value from a particular set of data; eventually this value is to be interpreted to make decisions.

The need for data analysis is apparent since the digital universe is expected to grow 50-fold in terms of data by 2020, yet today only about 1% of the data is analyzed.

To capitalize on data monetization, we can employ the following approaches:

An improvement in internal business processes – To locate synergy between different results, one result may provide some information, but coupled with another piece of result obtained, the synergistic outcome may be far more valuable.
Wrapping information around core products and services – This can be accomplished through understanding the target customer (analysis of their online presence can yield valuable information), and many companies are already indulging in these practices.
Trade of information to existing markets – This can often lead to be the most profitable of the three approaches, depending on the information, which it possesses.
Developing a technological structure – A technological infrastructure, capable enough to churn a real time data and provide real time results would be a boon to any business.

Already 70% of the large institutions purchase external data and monetization of the information asset is still in its infant stage. According to a study performed by Gartner, Data Monetization will be performed by 30% of the companies or more and in a survey conducted by IBM, data monetization was found to be among top 5 priorities of an organization.

The above clearly implies the upward trajectory growth in the near future in this industry, and with the application of the above-mentioned approaches, an effective strategy can be implemented by any organization hoping to be a part of the Data Monetization phenomenon.

Get the best Big data certification with our specialists at DexLab Analytics.

Interested in a career in Data Analyst?
To learn more about Machine Learning Using Python and Spark – click here.
To learn more about Data Analyst with Advanced excel course – click here.
To learn more about Data Analyst with SAS Course – click here.
To learn more about Data Analyst with R Course – click here.
To learn more about Big Data Course – click here.

Sherlock Holmes Has Always Been a Data Analyst. Here’s Why

Posted on April 13, 2017May 28, 2018 by Dexlab

The job of a data analyst or scientist revolves around gathering a bunch of disorganized data, and then using them to build a case through deduction and logic. Finally, following that you will reach a conclusion after analysis.

Below quote from Sherlock Holmes is relevant –

“When you have eliminated the impossible whatever remains, no matter how Improbable it is must be the truth.”

tumblr_mdorpe1mnr1qf5zmno1_500

He always started each case by focusing on the problem.

The problem would sometimes arrive in the form of a letter, sometimes as an item in the newspaper, but most often, it would announce itself by a knock at the door. The client would then present the mystery to Holmes and he would probe the client for salient information. Holmes never relied on guesswork or on assumptions. For Holmes, each new case was unique, and what mattered were reliable and verifiable facts about the case. These gave the investigation an initial focus and direction.

Deduction, Reasoning & Analytics

“It is a capital mistake to theorize before one has data. Insensibly one begins to twist facts to suit theories, instead of theories to suit facts.”

Similarly a data analyst is expected not to assume or formulate theories, which can make the reasoning biased. In his stories, Sherlock Holmes demonstrates his keen powers of observation and deduction from data in front of him. He can decipher how the light enters in Watson’s bathroom based on how his beard is shaved; he attests one person has lived in China from one of his tattoos; he discovers previous financial situation of a man who he had never seen before just looking to the hat the man had just used.

A data scientist has powerful computational and statistics tools that help him finding patterns amid so much data.

In the end, a data analyst’s introduction can be similar to what Sherlock said:

“My name is Sherlock Holmes. It is my business to know what other people do not

know.”

–Team Cosmos

You can learn more about Data analysis by taking up Data analyst certification courses. DexLab Analytics also offers Business analyst training courses.

Interested in a career in Data Analyst?
To learn more about Machine Learning Using Python and Spark – click here.
To learn more about Data Analyst with Advanced excel course – click here.
To learn more about Data Analyst with SAS Course – click here.
To learn more about Data Analyst with R Course – click here.
To learn more about Big Data Course – click here.

Harnessing Big Data for Water Management

Posted on March 24, 2017February 25, 2019 by Dexlab

Appalling forces are re-establishing the relationship between humans and water.

In the past, communities developed slowly, while the weather remained constant. Water sources never depleted at tumultuous rates as it has today. Water is no longer a dependable resource. That’s why many countries and cities are embracing smart technologies to manage water efficiently and preserve it for the coming generations.

As we observe the United Nations World Water Day on Wednesday, 22^nd March, it is apt to assess the development being made in conserving this diminishing resource.

Today, the Internet of Things (IoT) – a blooming worldwide network of devices and appliances linked to the internet – has materialized as a propitious solution to save water and protect clean drinking water, especially in cities.

To begin our discussion, Netherlands is on its way to develop a pioneering program to address the relevant problems of increasing sea levels, surging number of droughts and the effect of extreme weather changes on its trains, bus networks and roadways, and the efficiency with which the entire nation tackles situations like this. The ambitious project, Digital Delta draws in local and regional water jurisdictions, top-notch scientists and proliferating businesses to implement Big Data technology for upgrading the systems of its €7 billion water management, while restricting the costs of preserving water by 15%.

Prophecies about Urban Centres

Plummeting freshwater resources: a serious challenge faced by the global population is now at its apex. An overwhelming 89 percent of the world population thrives on enhanced water supply systems, which results in a loss of more than 32 billion cubic meters of fresh water, through physical leakage. Thereby, more than 50 percent of world population will be vulnerable in water-stressed regions by 2025. And by 2040, the figures will further push the energy demand by 56%, making US the second highest energy consumer across the globe.

Saving Water Globally

In the meantime, most of the world cities should re-invent and re-structure their assets to pull together advanced functions encompassing different complex systems and to associate with new powerful allies. Urbanization comes with its own costs. Day by day, these networks are growing more complicated and even more expensive. By delving deeper into the interconnections of systems, the societies will be in a better position to grasp how to run them more efficiently.

Water has never grabbed eyeballs, as it has today. Many countries are not at all prepared to manage such burgeoning complexities of water management. Besides, water management authorities are constantly under pressure to harness their power for flood protection and drinking water standards.

Reality Check: Water demand is set to rise by 30% by 2030. Ever increasing population and swelling urbanization are the reasons behind such calamitous figures.

Smart City Technology – The Key to Urban Sustainability

New Jersey Institute of Technology (NJIT) revealed that by 2025 smart city technologies would multiply to an industry estimating $27.5 billion. Moreover, nearly 88 smart cities will develop by the end of 2025. Smart cities whirl around the concept of using improved, interconnecting technologies to make environment safe, lives easier and urban living cost-effective and more efficient.

Societies are enduring new weather extremes. It is the high time to use big data and analytical science to cure the growing complexities in managing our water systems. Smart technology is the only viable option that can take future generations towards a sustainable future.

Seeking data science courses online? Visit us at DexLab Analytics. We offer a wide array of highly interactive online courses in data science.

Interested in a career in Data Analyst?
To learn more about Data Analyst with Advanced excel course – Enrol Now.
To learn more about Data Analyst with R Course – Enrol Now.
To learn more about Big Data Course – Enrol Now.
To learn more about Machine Learning Using Python and Spark – Enrol Now.
To learn more about Data Analyst with SAS Course – Enrol Now.
To learn more about Data Analyst with Apache Spark Course – Enrol Now.
To learn more about Data Analyst with Market Risk Analytics and Modelling Course – Enrol Now.

Knock! Knock! It’s Time to Change Your Bad Data Habits

Posted on March 23, 2017April 13, 2018 by Dexlab

Do you follow your instincts instead of data and insights?

Do you prefer storing data in different databases, in separate formats with varying values?

Habits are subject to change. Though it may take some time, but eventually it evolves. Good and bad habits make a person. Good habits don’t demand attention, but bad habits often need to be looked into.

If you suffer from bad data habits, then you must make sure you deal with it. It has to be a thing from your past rather than a dominating present. After all, data is incredibly important for business organizations to proliferate and generate decent revenues.

As per Experian’s Data Quality Report, 83% of companies consider their revenue suffers from inaccurate and insufficient customer data. It happens because of time and money wastage on insubstantial resources, which leads to a humungous loss of productivity and profit.

Bad Data Habits: The Ugly Truth

Data is the essence of business. From email delivery to customer feedback to profit generation, the impact of data trickles from strata to strata.

Sadly, many companies fail to fathom the significance of data and continue storing data on multiple systems, instead of a single location, in various formats without actually knowing ways to handle it. This eventually results into huge data pile-ups, where the entire data silo becomes difficult to manage.

However, if you have the right tools and a zeal to ensure data quality, you can confidently manage your data, eradicate duplications and fix errors before they inflict damage to your fundamentals. Besides, prudent strategies, time-to-time reviews and absolute determination are necessary; read this article to gain more insights about how to work on your bad data habits.

Let awareness do the work

Detailed information about customers is crucial for better assistance and quicker efficiency. So, you should always tell your customer support team to derive more information about their customers in order to serve better.

Understand your data needs

What data is important for your business? Once you know that, you will be able to apprehend your customer’s needs and expectations more effectively. Moreover, be sure that the data is accessible to all those who really needs it, otherwise it won’t be fruitful.

Introduce Standardised Data Quality Policies

For high quality data, make sure you introduce standard data policies and procedures. Also, ensure that the people working in your organization are acquainted with the ways of recording and storing it.

Initiate Regular Reviews

Data degradation is common. Human beings commit mistakes. Hence, it is important to regularly review and cleanse data in order to avoid future discrepancies.

Integration and Installation of the Right Tools

Integrate your network to ensure the data is stored on one server, but accessible from multiple locations. This will help you get an entire picture of your company’s business performance over varied mediums. Install any of the improved Data Cleaning Software to make sure your data is free of duplicates and perfectly formatted right from the start.

To brush up your analytics skills, get enrolled in a Data analyst course. Visit DexLab Analytics.

Interested in a career in Data Analyst?
To learn more about Machine Learning Using Python and Spark – click here.
To learn more about Data Analyst with Advanced excel course – click here.
To learn more about Data Analyst with SAS Course – click here.
To learn more about Data Analyst with R Course – click here.
To learn more about Big Data Course – click here.

ANZ uses R programming for Credit Risk Analysis

Posted on March 10, 2017January 29, 2019 by Dexlab

At the previous month’s “R user group meeting in Melbourne”, they had a theme going; which was “Experiences with using SAS and R in insurance and banking”. In that convention, Hong Ooi from ANZ (Australia and New Zealand Banking Group) spoke on the “experiences in credit risk analysis with R”. He gave a presentation, which has a great story told through slides about implementing R programming for fiscal analyses at a few major banks.

In the slides he made, one can see the following:

How R is used to fit models for mortgage loss at ANZ

A customized model is made to assess the probability of default for individual’s loans with a heavy tailed T distribution for volatility.

One slide goes on to display how the standard lm function for regression is adapted for a non-Gaussian error distribution — one of the many benefits of having the source code available in R.

A comparison in between R and SAS for fitting such non-standard models

Mr. Ooi also notes that SAS does contain various options for modelling variance like for instance, SAS PROC MIXED, PRIC NLIN. However, none of these are as flexible or powerful as R. The main difference as per Ooi, is that R modelling functions return as object as opposed to returning with a mere textual output. This however, can be later modified and manipulated with to adapt to a new modelling situation and generate summaries, predictions and more. An R programmer can do this manipulation.

`Read Also: From dreams to reality: a vision to train the youngsters about big data analytics by the young entrepreneurs:`

We can use cohort models to aggregate the point estimates for default into an overall risk portfolio as follows:

A comparison in between R and SAS for fitting such non-standard models — Photo Coutesy of revolution-computing.typepad.com

He revealed how ANZ implemented a stress-testing simulation, which made available to business users via an Excel interface:

The primary analysis is done in r programming within 2 minutes usually, in comparison to SAS versions that actually took 4 hours to run, and frequently kept crashing due to lack of disk space. As the data is stored within SAS; SAS code is often used to create the source data…

While an R script can be used to automate the process of writing, the SAS code can do so with much simplicity around the flexible limitations of SAS.

`Read Also: Dexlab Analytics' Workshop on Sentiment Analysis of Twitter Data Using R Programming`

Comparison between use of R and SAS’s IML language to implement algorithms:

Mr. Ooi’s R programming code has a neat trick of creating a matrix of R list objects, which is fairly difficult to do with IML’s matrix only data structures.

He also discussed some of the challenges one ma face when trying to deploy open-source R in the commercial organizations, like “who should I yell at if things do now work right”.

And lastly he also discussed a collection of typically useful R resources as well.

For people who work in a bank and need help adopting R in the workflow, may make use of this presentation to get some knowledge about the same. And also feel free to get in touch with our in-house experts in R programming at DexLab Analytics, the premiere R programming training institute in India.

Ref – https://www.r-bloggers.com/how-anz-uses-r-for-credit-risk-analysis/

Interested in a career in Data Analyst?
To learn more about Data Analyst with Advanced excel course – Enrol Now.
To learn more about Data Analyst with R Course – Enrol Now.
To learn more about Big Data Course – Enrol Now.
To learn more about Machine Learning Using Python and Spark – Enrol Now.
To learn more about Data Analyst with SAS Course – Enrol Now.
To learn more about Data Analyst with Apache Spark Course – Enrol Now.
To learn more about Data Analyst with Market Risk Analytics and Modelling Course – Enrol Now.

Call us to know more

Gurgaon

Kolkata