info@projexel.co.uk

/info@projexel.co.uk

About info@projexel.co.uk

This author has not yet filled in any details.
So far info@projexel.co.uk has created 9 blog entries.

Speaking at the Global Predictive Analytics Conference

Implementing Predictive Analytics into Operational Workflows I will be presenting on April 3rd 2018 in Santa Clara, CA at the Global Predictive Analytics Conference.  My session focuses on how to build predictive analytics and integrate the model into your business.  I will examine two use cases: Customer Churn and Cross Selling and demonstrate the process to build the model from start to finish.  Where and how to engage with business teams to ensure the success of the project.  In addition, I will show how pilot projects build collaboration between the data science teams and business units to ensure both teams understand what is required for successful projects. For complete information on the conference - Predictive Analytics Conference Homepage

By |2018-02-27T07:14:09+00:00February 27th, 2018|Uncategorized|0 Comments

Text Mining and Sentiment Analysis of SuperBowl LII

Sentiment Analysis of Tweets from SuperBowl LII Do you own a business and wonder what people aka customers are saying about your company?  Using text mining and sentiment analysis enables you to uncover the words your customers are using and the positive or negative sentiment of those words.  Text mining involves taking text from any source and breaking it down into the core words.   Sentiment analysis then applies the score to the words from -1 (the worst sentiment) to 0 (neutral sentiment) to 1 (highest positive sentiment).  The scores of all the words found create the overall sentiment for that encounter. To show this in action, I ran sentiment analysis on Tweets the day after SuperBowl LII (2/5/2018).  In one example, someone tweeted "Congratulations Philadelphia SuperBowl champions".  The word champion has a positive sentiment and has a positive sentiment score of  .70.  When you take all of the words in [...]

By |2018-02-06T12:55:17+00:00February 6th, 2018|RapidMiner|0 Comments

Choose the Best Power BI Version for Your Organization

Selecting the Power BI Version for Your Business Microsoft's Power BI is their flagship product for data visualization.  It enables businesses to connect to hundreds of data sources, build and deliver dashboards, and share content with others in your organization.  Since it is cloud based, users can view the information from inside their network or on mobile devices from outside the network.  Understanding with Power BI Version you should select and how they interact can be difficult.  There are two core versions of the product, Power BI Desktop Free and Power BI Professional.  Power BI Premium creates a dedicated cloud environment for your users to access the content. Power BI Desktop Free The Power BI version: Desktop edition is free for use and it great for people that want to try the product on your own data.  You can build fully functional reports and dashboards, however, you cannot share your [...]

By |2018-02-05T07:15:48+00:00February 5th, 2018|Power BI|0 Comments

RapidMiner Market Basket Sample

RapidMiner Market Basket One method to create a targeted cross selling model is to use historical customer information and apply the prediction to existing customers.  In this example, I will be using fictitious customer account data for a financial institution such as a bank or credit union to create a RapidMiner Market Basket predictive model.  The Marketing department wants to send out targeted mailing and phone call campaigns to customers most likely to need an auto loan.  The available data includes information on each unique account along with flags that indicate use (1 used, 0 not used).  Other fields count the number of inbound calls, late payments, or number of months as a customer. Sample Financial Data Fields Account ID                                       10. Holiday Club Indicator Account Origin Indicator            [...]

By |2017-10-09T07:01:42+00:00October 9th, 2017|RapidMiner|0 Comments

Power BI Leveraging Tabular Models

Power BI Direct Query Power BI can be used in one of two modes to access data.  The import option loads data from the source data to the Power BI model.  Queries are then processed directly against the data in the model.  Using the DirectQuery option, on the other hand, leaves at the source and Power BI queries the data as needed.  For smaller tables using DirectQuery can be a good option to leverage when you do not want to build a data refresh process into Power BI.  Source systems can potentially be queried on demand and provide users with the most up to date data as possible.  DirectQuery does have limitations that you need to be aware such as connecting to a single database only, time intelligence is not available, and there is a million row limit. For complete benefits and limitations of Power BI see - https://powerbi.microsoft.com/en-us/documentation/powerbi-desktop-use-directquery/ Power BI Tabular [...]

By |2017-10-02T07:05:09+00:00October 2nd, 2017|Power BI|0 Comments

Cross Selling and Predictive Analytics

Increase Revenue Cross Selling with Predictive Analytics Understand how data mining and predictive analytics can help you target the best customers for cross selling or up selling opportunities?  By building a predictive analytics model that leverages historical data from your company.  A model can be built and applied to your active customer base that identifies your best offer for a customer.  We can get you next best offer models off the ground in 10 days.  See what is possible with machine learning to increase your revenue and decrease expenses.     Learn more about our Data Quick Start Solutions See how to leverage Data Mining to Improve Business Operations Learn more about Machine Learning

By |2019-10-08T18:57:59+00:00June 25th, 2017|Data Mining|0 Comments

Predicting Employee Churn with Data Mining

Use Data Mining to Identify Employees at Risk of Churn For organizations that have a lot employees that are in high turnover positions.  Predicting employee churn with data mining can help to reduce and retain top talent.  By collecting data on employees and then building a predictive model using employees that have left the organization.  You can create models that will give you new insights into the characteristics of employees that are at risk of leaving.  By having this score you can then match up the performance of the employee to determine options to keep your talent and prevent them from leaving.  For example a call center, sales team, or temporary agencies could all benefit from building models to determine why employees are leaving. Build the Model For this example model, I used a sample dataset that contains various information for each employee.  This data contains both customers that are [...]

By |2019-08-10T20:29:39+00:00May 11th, 2017|Churn, Data Mining|0 Comments

Using Power BI to Visualize Houston Crime Stats

Houston Crime Data The city of Houston provides high level details on crime statistics via Excel files on the police website.  These statistics are stored in monthly files available via Excel or Access.  In order to better understand the crime data I created a single Excel file that stored the data from August 2016 to December 2016.  The data is formatted as shown.  I wanted to see what type of information I could learn by using Power BI to Visualize the data. Using Power BI to Visualize the Data Connect to the data in Power BI directly to the Excel file.  To explore summary information build simple data grids that expose the total number of records grouped by hour and date totalling 53,614 offenses.   You should expect to see 24 values for the Hour column and only records from August to December 2016.  By reviewing the data, the hour data [...]

By |2017-03-27T06:30:08+00:00March 27th, 2017|Power BI|0 Comments

Increase Data Value with Master Data Management

Master Data Management and Data Value Master Data Management (MDM) is a system that enables business critical core data to be entered and maintained through a central application.  Security and tracking of the data value changes are built into the process and allows tracking the history of values.  Data that is vetted and approved can then be used in the enterprise by other applications.  For instance, you can create a master data set for products.  Each product would have a unique identifier and be a single view of the product. When a new product is created or an existing product is updated the updates go into the MDM application.  Once the data is approved, the information is then available to be sent back to the source applications.  The applications can then leverage the data and you have a cleaner more accurate view of products. Sample Master Data Management Flow  Example [...]

By |2017-03-15T20:51:09+00:00March 15th, 2017|Master Data Management|0 Comments