Wednesday, May 2, 2018

Enhencer Predictive Storyteller - Data Analytics Live Demo

Enhencer is a visual data analytics and predictive intelligence platform focuses on the business intelligence and data visualization concepts after the emergence and popularity of the machine learning methods. With Enhencer You no longer need out-of-fashion summary tables and plots, prediction algorithms those are not always accurate, and bulky software to manage prediction processes. Enhencer generates predictive functions that you can use in your action plans by clearly showing the causalities in the data. Enhencer is also an analytical presentation tool which provides you with an elegant and interactive dashboard to display reports.

There is a live demo of Enhencer online you can try on your own. If you have any question or a request for demo, you can fill the request for a demo form here or email Enhencer. For more info, you can also refer to Enhencer Predictive Intelligence Online Help.

# Open Enhencer's Customer Satisfaction Data Analytics live demo.

Enhencer screen is divided into 3 panels.

Left Panel in the analyze screen contains all the variables from the data. The green highlighted variable indicated the particular variable is selected as “Target Variable” for the analyzes. You can simply change the target variable by simply clicking a different variable.

Currently, Customer Status variable is selected. This variable is categorical and has two possible values : Retention and Churn. As you can see, overall customer retention is 54.2% and churn is 45.9%.

In order to obtain deeper insights from the data, users need to use the “Enhance” task. Behind the curtain Enhencer used Machine Learning Algorithms to fetch the deeper insights from the data.

Enhance task can be performed by clicking the “Enhance” button. Enhance lets you to use the machine learning algorithm to dig out the dapper insights from the data.

# Click Enhance button.

Upon clicking the “Enhance” button a new window will pop up named “Select”. You need to select the relevant variables to observe the effects of the selected variables on the target variable.

Blue highlighted variables are the ones that are currently selected for the Enhance task. The deselected variables are represented with the non-highlighted ones.

#Click ALL in Select window to select all variables. Click OK at the bottom of Select Window.

Right side of the analyze screen is reserved for hierarchy view. When “Enhance” is active the tree view is presented to the users. Here Relations and effects of other variables with the target variable can be observed.

Leaf represents a segment and the features above the leaf represents the path to that segment.

Tree View branches from the most important variable effecting customer status to least. Currently, overall is selected which is 4,000 data point size.  The first leaf shows the online usage and the split is 14.9895. As you can see, 26.1% of the customers have less than 14.9 hours online usage and their churn is the highest at 84.9%.

# Select Retention from Target Choice to let Enhencer perform segmentation.

Enhencer will create the segments with the highest lift at the top.

Segments is a powerful tool that shows segments of the target variable and their features. When “Enhance” is active segments can be accessed by simply clicking the “Segments” button. If target variable is categorical like this example then in order to access the segments the user needs to choose one of the target choices form the “Target Choice” drop down menu. For any other variable type, it can be accessed directly.

Right side of the analyze screen in this case shows all the segments available for the target variable. Segments are sorted from highest gain to the lowest gain.

# Click Segment 1 to see its properties. As you can see below, this segment has the highest lift.

The proportion of the target choice in the selected segment compared to the overall population is represented by “Gain & Lift” measures. For this instance, in segment number 1 among 271 customers 90.8% of the customers are retained which is 1.68 times (67.6%) higher than the overall population with 54.2% retention rate.

In Segment 1, you can see the highest retention segment. These are people with 14.9 hours or more online usage, primary social network Facebook, and so on.

You can see which variables effect the target variable most using Effects View.

# Click Effects button.

Effects is a powerful tool that shows the variables that effects the target variable the most. This means among hundreds of different factors from the data these are the ones to affect the target variable the most.

When “Enhance” is active effects can be accessed by simply clicking the “Effects” button. The right side of the screen shows the effects of other variables. The variables are sorted from “High Dependency” to the “Low Dependency”.

When “Effects” is active users can also take benefit of prediction task. In Enhencer you can either predict by simulation or by uploading a new dataset.

In order to take benefit of the “Predict” task user must have [A] “Enhance” active and be on the [B] “Effects” tab.

Effects is a powerful tool that shows the variables that effects the target variable the most. This means among many different factors from the data these are the ones to affect the target variable the most. Moreover, these are the variables that the user can use to predict new cases either by simulating a case from the variable list in the right or uploading a completely new data.

If the target variable is categorical as in this case, Target Choice should be selected. In our example, Retention is already selected.

Prediction can be of two types. One is the classical test data method, where prediction scores are observed for a new dataset after the model is trained. Another is to simulate a very specific case just to observe how the data scores might change or how specific variables contributes to the prediction scores. This example is the latter one, simulating a certain case.

# Select Online Usage above 20 hours and Facebook as the only primary social media account. Click Predict.

Enhencer predicts that you will have 75% chance to retain this type of users.

Monday, April 23, 2018

Improve customer retention and reduce customer churn by self service data analytics

To boom in today’s competitive world, a business must know its customers inside out. To understand your customers is to understand their motivations, their desires, and their fears.

Your customer data can make you discover a lot about your customers if you can use proper customer data analysis tools. With such a tool, you can know why do people buy your products and services and what motivates them and what drives them away.

Customer Retention & Churn

The most precious assets for a business are it’s customers. However, the most important customers are not the ones that a business gains, but the ones who stay longer. It is one thing to count how many people have signed up or walked into store for the first time and quite another to understand what makes them coming back or leave.

Customer retention refers to the ability of a company or product to retain its customers over some specified period. High customer retention means customers of the product or business tend to return to, continue to buy or in some other way not defect to another product or business, or to non-use entirely. Selling organizations generally attempt to reduce customer defections.

Enhencer Self-Service, Visual Data Analytics

Enhencer self-service visual predictive platform selects and runs the best ready-made machine learning algorithm as users click on the visual dashboard. This helps organizations ;

  •     to reduce the data analytics time to minutes from days,
  •     to reduce dependency on expensive data scientist resources and statistical tools
  •     increases the use of data analytic so value extracted from data analytics is increased.

With Enhencer, you can take the power of Customer Retention & churn analysis at your own hand :
  •     Learn Customer lifetime value for each customer using the most powerful Machine Learning Algorithms.
  •     Predict the lifetime of your customers using the Predictive Power of Enhencer.
  •     Obtain precise segments of customers regarding Retention & Churn.

Customer Retention & Churn Analysis Example

You can integrate your customer database to Enhencer and perform customer retention & churn analysis within a few clicks.

Customer Segmentation

In this example, the customer loss is 45.8%. 

You can select the customer properties to let Enhencer automatically create customer segments where loss is minimum and maximum.

Enhencer will select the best ready-to-use machine learning algorithms to create customer segments for you. The top segments are were  customers are more loyal and it goes to bottom, the customers become increasingly less loyal. For example in Segment one, retained customer rate is 75% higher than the average and there are 96 customers in this segment.

In this segment, you can see the customer details. For example in Segment 1, online usage is greater than 14.9 hours per week, primary social media accounts are Youtube, Qzone, Twitter, Instagram or  Vkonta, 3 years cummulative complaint number is less than 3, etc ... Churn in this segment is as low as 5%.

You can extract the specific customers in each segment to use outside Enhencer.

Predictive Intelligence

Enhencer also helps business users to do predictive analytics. In the predictive panel, you can select a customer group with specified properties and see the probability of them to leave. This enables you to decide which customer groups to focus i you want to minimize customer churn.

For example below, customer with primary Facebook and Instagram accounts, obtained by 30 days free trial and aged between 18 - 26 has a probability of 52% of being a lost customer.

You can find out the Customer data analysis capabilities of Enhencer here. You can also request for a demo.

Friday, April 20, 2018

Self-service predictive visual data analytics

You are invited to Enhencer Predictive Visual Storytelling webinar on May 4th 2018 at 10:00 AM GMT +8:00.

In this free event, you will discover how self-service visual data analytics can help you to derive actionable insight from data with no data science experience. Enhencer self-service visual predictive platform achieves this by selecting and running the best ready-made machine learning algorithm as you explore your data by click on the visual dashboard. This helps companies to;
  • to free business users from data scientists and perform advanced data analytics
  • to reduce the data analytics time to minutes from days
  • to reduce dependency on expensive data scientist resources and statistical tool
  • increases the use of data analytic so value extracted from data analytics is increased
You will also have a chance to see a demonstrations of Enhencer. Please click register to join.

Event Information

Date :May 4th 2018, 

10:00 – 10:45 AM GMT (Singapore / Malaysia / Hong Kong)
09:00 – 09:45 AM GMT (Indonesia / Thailand)

Turkish Technic Selects ICRON's MRO Planning Software

Turkish Technic has selected ICRON’s MRO Planning software to optimize routine maintenance packages for aircraft. Using the software’s Maintenance Cards Interval functionality, Turkish Technic will be able to optimize balancing the distribution of task cards for planned maintenance. According to ICRON, this will increase productivity by minimizing early task card application and increase aircraft flight time.

“One of the most challenging problems for airlines and MRO companies in [the] aviation industry is to apply several maintenance cards that have different application intervals by keeping the duration of aircraft on the ground at a minimum,” says Ahmet Karaman, Turkish Technic’s general manager. “After a detailed research process, we have chosen ICRON for the optimization of our maintenance cards.”

The software, which is part of ICRON’s graphical scheduling and modeling system (GSAMS) platform, has functionality to coordinate schedules for workforce, spare parts, equipment and more. ICRON says it allows for real-time visibility of all day-to-day operations while reducing turnaround times and cost. The software’s user interface supports mobile devices and can run on the cloud, although the company says most customers prefer local server architecture for security reasons.

Turkish Technic says the goal with implementing the new software is to keep aircraft in the air as much as possible by decreasing maintenance turnaround time and minimizing maintenance occurrences at the macro level. According to a spokesperson for the company, ICRON’s software will support these goals by determining the maintenance check concept in a very short time for a new fleet and analyzing the plausibility of check intervals for the existing sub-fleet types.

Maarten Baltussen, ICRON’s chief revenue officer, says the new contract with Turkish Technic is a milestone in the company’s 25-year history. “After having SAESL, the MRO division of Singapore Airlines (Singapore Airlines Engineering Company), as a customer for several years, getting Turkish Technic on board means the recognition of ICRON as a market leader in airline MRO solutions,” he says.

According to ICRON, SAESL’s implementation of its MRO software has dramatically reduced repair turnaround time by automatically updating and optimizing the company’s schedule six times a day in less than half an hour.

Turkish Technic aims to have writing of the software’s code completed at the end of April and it will be designing user interfaces in the meantime. The company’s goal is to go live with the new optimization tool by the end of May.

Only 50% of companies can measure the cost of their data, ICRON survey shows

50% of companies are not able to measure the cost of their data, according to the results of a survey conducted by ICRON, a leading provider of Optimized Decision Making and Supply Chain Optimization software solutions. The survey, which was completed by 165 executives at the IoT EurAsia 2018 event held in Istanbul last week, revealed that approximately half of companies – and only 35% in the manufacturing sector and 43% in the services sector – can accurately gauge their data costs, which may include costs for data collection, data cleaning, data updating, and data storage and access.

The survey also showed that only 68% of the data collected by companies is considered to be reliable and of good quality, while 32% of the data is thought to be unreliable and of poor quality. Only 12% of the respondents said that all the data that their companies collect is reliable and accurate. Furthermore, the group of executives who admitted that they don’t know the cost of their companies’ data also said that only 62% of their data is reliable and of good quality – which means that around 38% of their data costs are related to data that they deem to be unreliable and of substandard quality. 

Alfred den Besten, ICRON’s Chief Marketing Officer, commented: “The results of our survey are fascinating, as such a high percentage of respondents stated that they don’t know what the true cost of their data is and that they think their data is not reliable and of subpar quality. This means that many companies are burning money on collecting and maintaining useless data, and that unreliable data is being used to make important business decisions – and this poses a major risk. To be successful, companies must be able to assess the cost and improve the accuracy of their data and use their data to make the best possible decisions.” ICRON’s President A. Tamer √únal – who gave a presentation at the IoT EurAsia event on the topic of how to “Instantly transform your data into optimized decisions” – remarked: “Companies today have access to a tremendous amount of data from various sources including IoT devices and back-office systems, and data is the key driver of their business decisions.

The fact that so many executives don’t have a handle on their data costs and don’t trust the reliability of their data demonstrates that there is a real need for systems and solutions that enhance data utilization. ICRON’s groundbreaking optimized decision making platform does exactly that, enabling companies to use their data to automatically generate optimal plans and projections and make optimized decisions that minimize costs and maximize productivity and performance.”

 ICRON will be releasing the full results of the survey in the coming weeks.

Thursday, April 19, 2018

Predictive visual storytelling - Data analytics for business users without data science experience

Today, many companies collect huge amount of data which can add tremendous value if data analytics is applied on it. Unfortunately, predictive modeling and machine learning algorithms requires data science expertise and/or specialized statistical tools. These traditional resource are expensive. Many companies cannot afford to keep such employees. Even if they can, the process is rigid. A business users needs new data analytics requirement, he / she needs to ask it from data scientist and wait for the scientist to come up with the new model.

Enhencer Predictive Visual Storyteller is a self-service visual data analytics for business users to derive actionable insight from their data in a few clicks and with no data science expertise and coding.  Enhancer's visual dashboard is easy to use with clicks while best ready-made machine learning algorithms are run in the background in each click.

Enhencer offers segmentation using ready-made machine learning algorithms. Enhencer explores and provides best segments for your target objective no matter the complexity of the data. Enhencer offers instant actionable insights. Users can simply upload their data to Enhencer and within a few clicks and minutes can perform data analysis which requires days to do with traditional data analytics tools.


Suppose that you have integrated your CRM to Enhencer. You want to analyze the customer churn & retention. Suppose that you have a field in your data named customer status which can be "lost" or "existing". Suppose that for a selected group of customers, 48% are lost.

Your CRM holds customer data with many information like age, gender, income, how long / frequent customer uses a service, customer source, customer location, etc. By segmentation, you can find out what segments of customers are retained most and what segments of customers are lost most.

With dozens or even hundreds of properties in your data, it is difficult to intuitively segment the customers. You don't know which categories are significant in customer retention and which are not. Is age a factor? Customer source? Gender?

Below video shows the segments generated by Enhencer. You simply select the value (here customer loyalty) to analyze and Enhencer automatically segments them. Top segments mean which categories of customers are most loyal and bottom segments show the least loyal ones. In the example below, first segment is 110% gain on average which means they are more than twice loyal compared to average loyalty. This segment is :

Salary Amount > 10,397
Age > 29
Gender = Male
Nationality = Japan or UK

The least loyal ones are :
Salary <4,031.
Customer Class = Silver
Nationality = US, Japan, France, UK and Italy.

Locating these significant customer properties among dozens and even hundreds of categories you have in your CRM is difficult if you do not have data analytics. With this info data analytics provides, you can have an action plan (i.e. target high income bucket more or investigate why Silver customers in certain countries are least loyal).

You can also perform predictive analytics in Enhencer on fly. For example, you can select several properties of customers (age range, gender, location, class, nationality, etc ...) and ask Enhencer to predict the probability of this customer to stay loyal to your company.

The platform is available on cloud by monthly subscription or if required can be installed in-house. You can request a demo here.

Tuesday, August 1, 2017

Data Analytics for Online Shops

Making shopping a smooth and easy experience is the goal of many online shops. But how can easy website navigation be optimized? Unlike the physical shops, you cannot talk to the sales people in the online shops and a customer should find his or her way through the online shop. And unlike pysical shops, online shops can have hundreds of thousands of visitors every day.

To optimize the shopping experience, some important questions should be answered :

  • Why do customers put products into their shopping cart and do not buy them at the end?
  • Was it because of the sales process or he/she liked another product simply better?
  • What impact has a customer's drop from a detail page?
  • Where are the differences in customer behavior depending on the different product groups,
  • Customer types or assortments?
  • What are the figures compared to the previous year?
  • Were there any technical errors? Was the accessibility of all pages always guaranteed?

Traditionally, answering these questions require a lot of work and usually takes a few days a month to prepare answers and presentations for the management. Since the process is slow and requires many man-days, most companies cannot perform it anytime they want or in the frequency they need.

German business consultancy company Mayato automatize this process using data preparation, analytics and visualization tools.

The company extracts data from the operational database to in-memory, ultra-fast analytics database named EXASOL. Traditionally, large volumes of data need to be extracted from the database, loaded into R statistical language based scripts and run; and then loaded back to database for analysis and visualization.

Markus Dill, Managing Director at Mayato, explains the importance of good analytics for companies in the manufacturing sector and why having an analytic database that is low-maintenance such as EXASOL is critical for business success.

But EXASOL has built-in R capabilities so R scripts can be run on EXASOLs ultra-fast and high performance analytics environment. The company uses Talend ETL tool for automated data extraction, transformation and load. The data extraction, crunching (using R) and data visualization (in Tableau software) are all automated without human intervention.

The combination of Talend, EXASOL and Tableau fully automated the process and reduced its report generation cycle from days to hours.