Predictive Analytics: Extracting Big Value from Big Data

Embed Size (px)

Text of Predictive Analytics: Extracting Big Value from Big Data

Predictive Analytics: Extracting Big Value from Big Data

2016 RapidMiner, Inc. All rights reserved.May 24, 2016Featuring Howard DresnerPredictive Analytics:Extracting Big Value from Big Data

#1 Modern Platform toTurn Data into a Strategic Asset2016 RapidMiner, Inc. All rights reserved.

2016 RapidMiner, Inc. All rights reserved.- # -

1

Speakers

Howard DresnerChief Research OfficerDresner Advisory Services

Lars Bauerle Chief Product OfficerRapidMiner

2016 RapidMiner, Inc. All rights reserved.- # -

Housekeeping Recording will be available within 1-2 business days, link will be emailed to you You may type your questions in the Questions panel on the screen at any time We will leave time at the end for a Q&A session

2016 RapidMiner, Inc. All rights reserved.- # -

Dresner Advisory Services

Advanced and Predictive Analytics and Big Data

Copyright 2016 Dresner Advisory Services, LLCwww.dresneradvisory.com

4

DefinitionsAdvanced and Predictive Analytics Includes statistics, modeling, machine learning, and data mining to analyze facts to make predictions about future, or otherwise unknown, events.

We define big data analytics as systems that enable end-user access to and analysis of data contained and managed within the broader Hadoop ecosystem.

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

6

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Copyright 2016 Dresner Advisory Services, LLC

Dresner Advisory Services

Advanced and Predictive Analytics and Big Data

Copyright 2016 Dresner Advisory Services, LLCwww.dresneradvisory.com

20

2016 RapidMiner, Inc. All rights reserved.May 24, 2016Lars BauerleChief Product OfficerRapidMinerforAdvanced/Predictive Analytics and Big Data

#1 Modern Platform toTurn Data into a Strategic Asset2016 RapidMiner, Inc. All rights reserved.

2016 RapidMiner, Inc. All rights reserved.- # -

21

RapidMiner is #1 OPEN SOURCE

Leader

2016, 2015 & 2014

Gartner Magic Quadrant for Advanced Analytics PlatformsStrong Performer

2015

Forrester Wave on Big Data Predictive Analytics

Innovation Winner

2015

Wisdom of Crowds for Advanced & Predictive Analytics, Big Data Analytics &End-User Data Preparation

#1 Open-Source Platform

2015, 2014, 2013

Data Mining & Analytics Software Poll

2016 RapidMiner, Inc. All rights reserved.- # -

RapidMiner is UNIQUE

Open-Source Innovation

Cutting-edge data science platform designed for the Big Data era

Frictionless Operationalization

Prescriptive analyticscloses the loop between insight & actionLightning-FastData Science

Seamless orchestration accelerates predictive analytics lifecycleSelf-Service Predictive Analytics

Effortless & guided design democratizes data science

2016 RapidMiner, Inc. All rights reserved.- # -

ACCELERATES Time-to-Value

Data Prep Speed & optimize ALL dataexploration, blending & cleansing tasks

OperationalizeEasily deploy & maintain models and embed analytic results

MODEL & VALIDATERapidly prototype and confidently validate predictive modelsData Prep Speed & optimize ALL dataexploration, blending & cleansing tasksConnect to any data source, ANY FORMAT, AT ANY SCALE support for All major BI, DATA VISUALIZATION & Business applications

2016 RapidMiner, Inc. All rights reserved.- # -

RapidMiner significantly accelerates the time to value for data scientists and business analysts alike.

We cover the building of complete analytical workflows - from data prep to modeling to operationalization -in a single environment or a single unified platform, so our customers & users dont have to go from tool to tool as they do with a lot of other vendors.

This means there is no break in the process when coping with the different phases of an analytic project so the prototype environment is the same as the production environment - which significantly speeds the creation of predictive analytics.

We can easily connect to any data source regardless of type, scale or location - including relational databases, Hadoop, social media, Salesforce, and hundreds more.

We offer robust data exploration functions for quick data discovery & our prep functionality not only covers the basics, but also advanced method's for optimizing predictive models.

Rapidly prototype & confidently validate predictive models

Our visual design interface, make it easy to interact with and modify information at any point in the modeling cycle We accelerate model creation with over 1500 available operations and allow users to combine different operators and save repetitive tasks as building blocks to reuse over and over again

RapidMiner is the only visual platform for machine learning which delivers honest performance estimations you can trustOur Modular cross-validations and preprocessing models allows data scientists or advanced business analysts to accurately and appropriately estimate model performance.

And finally and most importantly, for the third phase of the lifecycle operationalization - we let users embed their predictive insights into almost ANY business process or Data Visualization application, so that actions can be executed on to ensure continued value to help drive revenue, cut costs and avoid risk!

So the key takeaway her is that: RapidMiner helps users to get through the design process faster than ever before. So they can spend more time doing things they really enjoy - like exploring new solutions and achieving high quality, performance analytics 24

STREAMLINED Data Preparation

Speed & optimize ALL dataexploration, blending & cleansing tasks

A powerful chart engine offers statisticaloverviews, graphs & charts for data exploration

Rapidly import, combine and transform structured & unstructured data for deeper predictive insights

Accelerate advanced data blending tasks with powerful feature weighting, selection & generation

Expertly cleanse data with anomaly & outlier detection, missing value handling and normalization

2016 RapidMiner, Inc. All rights reserved.- # -

2016 RapidMiner, Inc. All rights reserved.- # -

. RapidMiner offers the most powerful data preparation capabilities of any visual machine learning platform on the market today,

Our data exploration tools display statistical overviews featuring basic statistic such as attribute name, type and identification of missing values, allowing users to immediately detect data patterns or quality issues.We also have a robust chart engine offering more than 30 different visualization techniques for data and models including: interactive data visualizations & advanced statistical and model visualizations such as: decision trees, self-organizing maps, etc

With RapidMiner, users are not limited to analyzing traditional tabular data, they can fully leverage ALL of their data for deeper predictive insights! RapidMiner can access and load unstructured data like texts, images and audio tracks. It can also extract information from these types of data and transform the unstructured into structured data with over 80+ text mining: processing & feature extraction functions. Alongside other tabular data, these data can be analyzed through all statistical approaches available in RM such as classification, regression and clustering techniques.

We provide the necessary data quality, integration, and transformation tools to ensure that the data is properly formatted and blended which not only speeds up the data prep process, but help optimize model performance

RapidMiner offers a host of operators for blending and massaging the data, for example:Filtering rows/examples according to range, missing values wrong or correct predictions or specific attribute valuesSet operators to join, merge, append, union or intersect diverse data setsWe have operators for handling meta data like rename or attribute role definitionAnd a select attributes operators for attribute weighting & generationAs well as feature engineering operators for -feature selection, creation & extraction

There are hundreds of operators in RapidMiner for expertly cleansing and formatting dataWe offer a variety of manual expressions as well as dozens of automatic approaches to cope with certain data properties,without the need for writing a single line of code or script. For example the filtering of rows or columns according to range, missing values, wrong or correct predictions, or specific attribute values. As well as the identification and removal of duplicates.In addition to the techniques listed above, RapidMiner offers a large number of sophisticated dimensionality reduction techniques, transformation operators for normalization and standardization and all sorts of type conversionsWithout this kind of advance