ICEPortal

Client:

AT&T Inc. is the largest provider both of mobile telephony and of fixed telephony in the USA and also provides broadband subscription television services. As of 2012, it is also the 20th largest mobile telecom operator in the world, with over 106 million mobile customers.

Business Need

Features Apps (FA) Widget is preloaded on Android phones and tablets released by AT&T. It’s placed on the tabletop of the devices and contains editorially-controlled carousel highlighting applications and games from AT&T and its content partners.

This version of FA for Android phones has a look and feel of the tablet version and provides an overall better end user experience. The widget encourages user engagement by providing fresh, timely and relevant content right on the home screen of the device. If the user sees a piece of content they would like to learn more about, or download, they might click on it and they are directed to the source storefront (i.e. Google Play) for download.

Akvelon was chosen as the sole contractor for this project. One of the reasons for this is the aggressive timeline Akvelon agreed on and the fact that Akvelon took full responsibility end-to-end for this fixed-bid contract. The project required a collaboration between two of Akvelon’s offices.

Kaggle.com is one of the leading platforms for predictive modelling and analytics competitions. Companies and researchers are able to post data sets and real world challenges which invite statisticians and data scientists to compete in building predictive models that best describe future outcomes.

Business Need

Porto Seguro, one of Brazil’s largest auto and homeowner insurance companies, posted a challenge on Kaggle.com to build a model that predicts the probability that a driver will initiate an auto insurance claim within the next year. While Porto Seguro has used machine learning for the past 20 years, they’re looking to Kaggle’s machine learning community to explore new, more powerful methods. A more accurate prediction will allow them to further tailor their prices, and hopefully make auto insurance coverage more accessible to more drivers.

Akvelon’s participation

A group of two Akvelon machine learning engineers and a data scientist enlisted on Kaggle.com decided to compete side-by-side with more than 5,000 teams for the top positions in the leaderboard. The competition submissions are evaluated using Normalized Gini Coefficient. The Gini Coefficient ranges from approximately 0 for random guessing, to approximately 0.5 for a perfect score.

The insurance group provided the same data set to all competition participants as a raw data set with 893,000 rows of 59 distinct data points, with little or no specification as to what the data actually represents. The Akvelon team went through several different iterations to identify the meaning of each of those data points, to cleanse the data and to reduce the number of variables to a manageable subset. If the data model has too many data points with little or no impact on the output (event of the driver filing insurance claim) the resulting model becomes too complex, and has an adverse impact on the performance to generate the proper output in a timely manner.

The raw data set with 893,000 rows of 59 distinct data points

The work involved in crowdsourcing competitions requires lots of: “try, fail, fail fast then make some changes and try again, repeat the entire process over and over” approaches. For example, the team experimented with several prediction models such as: Random forest, Logistic regression, Extra tree classifier, KNN, Naïve Bayes, Adaboost, Xgboost, Lightgmb, Catboost, Neural networks.

‘Competitions requires lots of: “try, fail, fail fast then make some changes and try again, repeat the entire process over and over” approaches’

One of the chosen approaches was the t-SNE (t-distributed stochastic neighbor embedding) which is a nonlinear dimensionality reduction technique that is particularly well-suited for embedding high-dimensional data into a space of two or three dimensions, which can then be visualized in a scatter plot. Specifically, it models each high-dimensional object by a two or three dimensional point in such a way that similar objects are modeled by nearby points and dissimilar objects are modeled by distant points. The image below shows the result of this analysis.

t-SNE result (yellow dots corresponds to 1, purple – 0)

The most promising alternatives were XGBoost and LightGBM which placed the team onto the top half of the competition leaderboard with a score of ~0.282. The top ranked team had a score of 0.290. Akvelon ‘s team score was 97.2% of the top ranked team. (The higher the score the better, with the maximum value of 0.5). The next step was to adjust the data model parameters such as (depth of the tree, number of estimators, size of the train and validation sets). Those experimentations raised the score to about ~0.284. With a model that was promising, it was the right time to go back and revisit the groomed data set and do a better approach in choosing which data point to include and which one to replace.

Further research and investigations helped the Akvelon team improve the models. Some of the improvements involved including a Neural Network which raised the score to ~0.285, placing the team in the top 2% of the entire competition.

After some additional tweaks, adjustments and learning from the past Kaggle winner teams approaches, the Akvelon team ranked in the top 1% with the score of 0.287 against the leader having 0.291 (98.6% from the top scoring team).

At the final stage of the competition, the organizers used 70% of the complete data set, unseen yet by any of the competitors. Each teams result against this new data set will determine the final score in the Leaderboard.

Kaggle Akvelon Machine Learning Standings

Porto Seguro Machine Learning Kaggle Competition Final Standings

The Akvelon Team placed 22nd out of more than 5,000 teams in the final standings after applying the complete data set. Finishing the competition in the top 0.5%.

Benefits and Results

Participating in the Porto Seguro Safe Driver prediction competition increased our expertise in the Machine Learning field. The trial and error portion of this project helped us refine data quickly, focusing on accuracy and details in every model. The data also provided a real world data set for a real world issue, so our models could be applied to different situations and everyday occurrences.

Finishing in the top 0.5% is a proud accomplishment when competing against more than 5,000 other teams.

If you would like to learn more about our Machine Learning capabilities and solutions, contact us today!

The Akvelon Team placed 22nd out of more than 5,000 teams in the final standings after applying the complete data set. Finishing the competition in the top 0.5%.

More Insights

The Winning Mix: Machine Learning and Human Creativity

The Internet Age has brought many discussions around the role of human capital and technology. The real answer lies in a mix of innovations in tech and human creativity. Read more.

Akvelon Teams with Microsoft to Bring Winning Data to Teams Worldwide

We’re proud to be collaborating with Microsoft to implement the newly released Sports Performance Platform to professional sports teams around the globe. Read more.

Advancing Sports Technology with the Seattle Seahawks

New technology was presented at Microsoft Data Insights Summit which will help in player injury prevention through through the use of data and visualization. Read more.

04 Oct ICEPortal

Client:

ICEPortal – Content Management Platform

ICEPortal is one of the largest content providers of travel and leisure-related visual content online. ICE Portal produces 360° virtual tours, WebShows, videos, and eBooks for the travel industry’s leading suppliers (hotels, destinations, cruise lines, vacation rentals, attractions, etc.) ICE converts content to the correct size, format, category,and brands it cheap mlb jerseys for delivery to multiple channels in many different languages.

Business Need

ICEPortal was mainly a photo and content wholesale jerseys production company seeking cutting-edge technology to change its business processes. Due to the rapid growth of its client audience, ICEPortal needed to upgrade technology, streamline content creation and management processes, and design an online wholesale jerseys China platform capable of supporting growth. Akvelon proposed an entire business model to meet those needs.

Solution

We developed a solution leveraging Microsoft .NET technology along with Microsoft SQL Server. It provided a scalable, manageable, and upgradeable web platform to lay the foundation for By ICEPortal’s success.
This solution provides ample cheap jerseys functionality and includes multiple features:

eBooks (electronic versions of books, brochures, catalogues with hi-resolution images)
Brochure Management Tool
Invoice Manager
Brochure Smart Links
360° Virtual Tours
Live Image Manipulation
Image Admin
Custom Features (based on specific business needs)
XML Interface

Following the system implementation, Akvelon signed an agreement to provide ongoing maintenance, support, and upgrades for ICEPortal. We are proud to provide Impressum 99.99% uptime for the service and 24/7 support.

This was the best platform we have ever used.

Benefits and Results

Improved overall company performance.
- Subsequently, ICEPortal has grown into a visual content distribution powerhouse, providing millions of content views per day with a monthly growth of 8%.
Increased company visibility.
- Based on the new business model, ICEPortal has established long-term partnerships with major industry players, including Orbitz, Travelocity, Priceline, Obrazy Expedia, etc.
Increased revenue.
- The advanced technology solution brought new and notable clients to ICEPortal. It helped make ICEPortal the easiest and most efficient way for hotels and resorts (such as Hilton, Marriott, Sheraton, Westin, and others) to deliver their content to 30,000+ leading travel websites and search engines worldwide.

Akvelon Ranks in Top 1% for Kaggle Machine Learning Competition

Interactive Darts Project

Akvelon Ranks in Top 1% for Kaggle Machine Learning Competition

Interactive Darts Project

Client:

Business Need

They completely reinvented the featured widgets, thank you!

Solution

Benefits and Results

Business Need

Akvelon’s participation

Benefits and Results

More Insights

The Winning Mix: Machine Learning and Human Creativity

Akvelon Teams with Microsoft to Bring Winning Data to Teams Worldwide

Advancing Sports Technology with the Seattle Seahawks

04 Oct ICEPortal

Client:

ICEPortal – Content Management Platform

Business Need

Solution

This was the best platform we have ever used.

Benefits and Results

Tags:

No Comments

Latest News

Akvelon Ranks in Top 1% for Kaggle Machine Learning Competition

Interactive Darts Project

Akvelon Projects with AZURE

AT&T Featured apps

Inrix

Latest Tweets

Akvelon

Client:

Business Need

They completely reinvented the featured widgets, thank you!

Solution

Benefits and Results

Business Need

Akvelon’s participation

Benefits and Results

More Insights

04 Oct ICEPortal

Client:

ICEPortal – Content Management Platform

Business Need

Solution

This was the best platform we have ever used.

Benefits and Results

Tags:

No Comments

Latest News

Latest Tweets

Socialize With Us

Solution 

Benefits and Results 