Land Value - Predictive Analytics

Download as pdf or txt
Download as pdf or txt
You are on page 1of 85

© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

PROPERTY RENTAL PRICE PREDICTION USING ALTAIR RAPIDMINER


Dr. Shidan C Murphy, August 29, 2023
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Dr Shidan C Murphy
Global Director, Banking and Financial Services
Location: Singapore

Biography
Dr. Shidan Murphy is an award-winning scientist, educator, pilot and data scientist with significant business experience in
the Asia-Pacific. He has published several papers published in international journals and written software to teach
statistical computing in R.

Beginning his career as a Research Scientist with the Canada Government, Dr. Murphy developed numerical methods to
predict how climate change, shipping patterns and shoreline modifications affect fish communities in the Great Lakes of
North America and in the Canadian Arctic.

Today, Dr. Murphy works towards solving the analytical issues facing financial institutions, retailors, utilities, insurance and
consumer-packaged good companies across Asia, India and Australia. Dr. Shidan Murphy oversees the pre-sales and
technical delivery of Data Analytics for Altair Engineering in the Asia-Pacific.

Dr Murphy holds a PhD from the University of Toronto.


©©Altair
AltairEngineering,
Engineering Inc. Proprietary and Confidential. All rights reserved.

Altair-at-a-Glance

$572M 74
FY22 Revenue In 27 Countries

3,000+ 150+
Engineers, Scientists, Altair and Partner
and Creative Thinkers Software Products

13,000+
Customers Globally
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Trusted by the World’s Leading Financial Institutions

Embedded in leading trading analytics software


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

13,000+ Customers Worldwide


Automotive Aerospace Financial Services Technology Energy Civil Engineering

Government & Defence Heavy Rail Industrial Goods Life & Earth Sciences Education Material Suppliers
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Advanced Analytics

Data Preparation Machine Learning Stream Processing & Unified Enterprise Platform
Visualization
Automate data collection, Leverage advanced Unified low code data prep,
data cleansing, and data machine learning and AI. Visualize real-time operational machine learning & visualization
transformation. Use trusted Understand what is performance. Spot anomalies, platform for experimenting and
and accurate data to make impacting your business. trends, and clusters in operationalizing AI/ML apps.
the right decisions seconds.

Altair® Monarch® Altair® Knowledge Studio® Altair Panopticon™ Altair® RapidMiner


Desktop + Server Desktop + Server Cloud native Cloud native, big data

Analytics Modernization
SAS Language Data Governance & IDE SAS Language &
Compiler Deployment Open Source

Run SAS Language & Streamline Dev-ops, Maintain, edit, and run new
Open-Source codes. govern data & access, and existing SAS language
create & manage data programs.
Altair® SLC® pipelines.
Cloud + Server
Altair® Analytics
Altair® SmartWorks Hub® Workbench®
6
Cloud + Server Desktop
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Altair Units
Revolutionary business model to enable customers to
get more from Altair software. D AT A
AN AL Y S T

1. Buy a pool of units


2. Use those units for any Altair software or
Altair Partner Alliance solutions
SUBJECT
3. Transfer the units between people so M AT T E R
EXPERT
anyone can use the software D AT A
SCIENTIST

ENGINEER DESIGNER

7
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

RapidMiner

8
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Altair RapidMiner: The Frictionless AI Platform

Domain Experts Data Experts IT Leadership

Enterprise Data Automated Visual Coding

Enterprise Data

PDFs, Excel,
Core Reports
Monitoring and
Reporting

IIoT

Enterprise
Applications

Synthetic Data Data Engineering Model Building Model Ops Operationalize

Analytics App Development Collaboration Governance Trust & Transparency


9
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

10
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Frictionless AI for Everyone


With our data analytics and AI platform, Center of
Excellence Methodology, and Altair Units.

No friction between users and data


Work with any data and centrally manage data assets. Build trust with
interactive apps and a wide array of techniques to explain models.

No friction between data and domain experts


Author the way you want depending on your skill level, use case and
productivity requirements. It’s end-to-end and interchangeable.

No friction from idea to production


No matter where data is coming from, or where insights need to go,
everything is easily distributable and consumable at scale.

No friction when tools, vendors or


infrastructure changes
Deploy easily on-prem or in the cloud and scale to any need.
Flexible licensing and usage with Altair Units.
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Upskilling Your People


With the Altair RapidMiner platform and
Center of Excellence (CoE) methodology. CRISP-DM

WHAT’S THE ACTUAL


Business PROBLEM?
CoE transforms how you use data Understanding
Creates alignment around a prioritized portfolio of AI use cases and
coaches through initial project success. Provides programmatic training.

Monitoring Data
Understanding
Academy builds expertise
Teaches data science foundations and principles through self-paced,
persona-based learning courses, pathways, and certifications.

Platform supports all people Data


Deployment
Preparation
Guides users through an end-to-end data science use case making
recommendations based on telemetry from 1M users. Makes AI visual
and understandable.

DO THESE
RESULTS MAKE
Evaluation Modeling
SENSE?

12
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

13
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Contents
• Brief Introduction to Data Science
• Comments on Data
• Data Preparation and Model Dataset
• Model and Validation
• Future Work
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

What is Data Science?


• Myth about Data Science
• Computer-driven process that looks for patterns in huge, complex databases and automatically
gives results

• Fact
• User-driven process that uses computers to help wade through enormous amounts of data in
order to discover useful patterns
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Why Do We Need Predictive Analytics… or ML or AI

16
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Your Beliefs are Definitely “Weird”


1. “Weird beliefs” are in fact common place and rarely extreme
1. Lucky Days, Numbers, etc
2. Many behavioral patterns serve very little practical purpose

2. People believe weird things because of our evolved need to believe


non-weird things.
o Dark forest, sudden noise – definitely not a branch falling!

3. Brain is wired to draw conclusions from noise to anticipate threats


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Evolutionary Rationale for Bad Decisions

• The predator is
staring at you.

• Better safe than


sorry

• Our environment is
evolutionarily new

• Decision-making
process hasn’t
caught up
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

19
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

20
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

WW2 Fighter Jets: Too much Armor is bad and so is too little

Armor:
• Increases Protection
• Reduces Speed
• Reduces Endurance
• Reduces Manoeuvrability
• Reduces Useful Load
• Increases Chance of
Getting Hit

21
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Where Should They Add Armor?

• Air Force examined


returning planes

• Mapped where the planes


were they were shot

22
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Where Should They Add Armor?

• Air Force examined


returning planes

• Mapped where the planes


were they were shot

23
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

24
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Importance of explaining variables and outcome

• Can we mentally explain observed relationships


• Not always critical – but can reduce incorrect conclusions
• Formulating the problem statement be very difficult
• There is a general movement to automate a lot of the model building process

25
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Statistical Significance
“The race is not always to the swift nor the battle to the strong, but that's the way to bet”
~ Murphy’s Law

26
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Who would you bet on? Team A

Team A Team B # Games in My Bet


Advantage Advantage Series

50% 50% 7 Team A/B


55% 45% 7 Team A
67% 33% 7 Team A
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

There Is A Sizable Chance The Inferior Team Wins

Team A Team B # Games Probability of


in Series Inferior Team
Winning
50% 50% 7 50% (p>0.05)
55% 45% 7 30% (p>0.05)
67% 33% 7 20% (p>0.05)
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Only a 23 Game Tournament Would Satisfy Superiority

Team A Team B # Games Probability of


in Series Inferior Team
Winning
50% 50% 7 50% (p>0.05)
55% 45% 7 30% (p>0.05)
67% 33% 7 20% (p>0.05)
67% 33% 23 5% (p<0.05)
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Our Desire to Draw Conclusions has Serious Implications


The “Replication Crisis”: To what extend can we trust scientific findings?

• “A large portion of replications produced • Ioannidis JPA (2005) Why Most Published
weaker evidence for the original findings” Research Findings Are False.
https://doi.org/10.1371/journal.pmed.002012
• “There is increasing concern that most
4
current published research findings are
false.” • Estimating the reproducibility of
psychological science
• “Failed papers circulate through the literature
https://www.science.org/doi/10.1126/science.
as quickly as replicating papers.”
aac4716
“Stand on the shoulders of giants”
• Camerer et al. Evaluating the replicability of
• More than 70% of researchers have tried social science experiments in Nature and
and failed to reproduce another scientist's Science between 2010-2015
experiments. https://doi.org/10.1038/s41562-018-0399-z

30
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Overview of Model Building Progress


Experiments/ Internet of Things
Operations
Simulation or Historical Streaming
Model Data Data Data

Model
Dataset

Validation
Data Machine Learning Predictions
On-going (algorithms, tools)
monitoring
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

CRISP-DM
Determine business Collect,
objectives and data describe,
• A Cross-Industry Standard mining goals explore and
verify
Process for Data Mining
quality of
• A tool - and application - data
neutral model
Champion/
• Encourages best Challenger Select,
clean,
practices
construct,
• Offers structure integrate
Integrate and format
• Encourages better, faster into data
results from data mining business
processes Select,
generate,
Evaluate how results build and
achieve business evaluate
objectives models
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Key Component to Machine Learning Models

Data Model Validation

• Low Quality Data • Lack of Statistical • On-Going Model


Significance Validation
• Influential Outliers
• Small Sample Sizes

33
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

DATA
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Data and Interpretation


Our desire to draw conclusions will mislead you

• Most of your time will be spent doing data transformation


o Plotting and Looking at Data
o Variable Creation
o Looking for new data to support your existing data

• Very easy to make decisions that are not helpful


o Correlated data
o Non-Significant data

• Most of your work at this stage doesn’t make it into the


final model
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Location of Offices
Plotted the Offices in Altair Panopticon

36
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Location of Property and Area (Rows = 119; Columns = 21)


Overview of Raw Data

37
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Rental Terms (Rows = 119; Columns = 21)


Overview of Raw Data

38
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Facilities and Orientation of Property (Rows = 119; Columns = 21)


Overview of Raw Data

39
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Suggestions for Raw Data Structure


Things can be fixed – but it adds unnecessary work

Suggestions
• Don’t add rows before data
• Column Names on only one line. This can confuse data types on import
• Don’t add a column number label (yellow line)
• Probably better to split address into parts

40
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Suggestions for Raw Data Format


Multiple formats within a column is asking for trouble
Comma or a Period as a number delimiter –
use only one – my preference is ,
The ‘ creates a text Lats\Longs have alternative formats
field. Better to use a =
Currently these fields
are all text so the
numbers display fine.
The issue is that if
you convert this to a
number in Excel the
zeros trailing the
periods are removed.
• Text
16.281.000 = 16.281

• Number

41
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Concerned about Data Quality

Rental space of zero area Predictions within predictions

Nothing wrong with this approach – but errors


tend to increase if underlying data are
generated from inaccurate models

42
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Outliers
Influence is greater on small sample sizes

43
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Outliers
Influence is greater on small sample sizes

44
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Outliers
Influence of one affects the many!

• Best way to find outliers is to plot the data


• There are various statistical methods that you
can use to find outliers in more complex data
• Don’t remove data you dislike – an outlier can
still be part of the actual distribution of data
• Lots of debate around when to remove outliers.
• My preference:
o Remove outliers with obvious measurement
error
o Structural reason to remove them

45
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Outliers removed in your data


Rental Space = 0 must be a mistake

46
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Outliers removed for “different” groups. Need a different model


Only Analyzed >200 m2

47
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Removed very expensive rents, IDR >100M

48
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

These are the filtering criteria


Data outside these ranges should get their own model or manual consideration

49
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Final Dataset (rows = 108 – a reduction of 11 points)


Reduced Dataset

50
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

QUICK REVIEW – WHERE ARE WE AT?


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Supervised Learning

• Key Features
• Basis of most ML techniques
• Datasets with known outcomes (labelled)
• Patterns in data are based on predicting the known outcome

Variable 1 …. Variable X Annual Rent


0.1969 132 390 100,000
… … … …
0.5179 173 1150 83,293
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

What are we predicting: Rent or Rent/m2


• Annual Rental Price
• Annual Rental Price/m2

53
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Data Preparation
Careful - what are we trying to predict?

Type of
Rental Rental
ON_KPKNL Area Rental Rental Price/m2
space (m2) Price/year
Object

KPKNL BATAM Building 1348 40,152,000 29,786


KPKNL BATAM Building 1530 33,717,000 22,037
KPKNL BATAM Building 2 16,651,000 8,325,500 = 16,651,000/2m
KPKNL BATAM Building 6 50,183,000 8,363,833 = 50,183,000/6m

KPKNL BATAM Building 87 18,341,000 210,816

54
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Location, Location, Location – but not here??


The Problem with small datasets

The best predictor of rental price What does this mean?


is if the unit has air conditioning -
which doesn’t make any sense

55
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Jakarta (Check the sent results carefully)


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Variables or Factors to include in the model


Logic suggests, location must be in the final model

57
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

All Environmental Factors have the correctly assumed direction


Small sample sizes, magnitude very different

3.5x 1.5x
1.5x

1.1x 2x

58
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Creating Environmental Factor


Making all factors equal – 1 out of a possible 5

Environmental Water Air Environmental


Parking Cleanliness Electricity System Conditioning Factor
Yes Good Yes Yes No =4/5, 0.8
No Good No No No =1/5, 0.2
Yes Poor Yes Yes No =3/5, 0.6

59
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Annual Rent and Rental Space (m2) is positively correlated


Appears the relationship exists and is reasonable to include

60
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Annual Rent and # Potential Visitors is positively correlated


Appears this variable is from another model

61
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Annual Rent and Operating Hours is not correlated


Does this make sense? I’m not entirely sure what this variable means

62
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Annual Rent and Operating Hours is not correlated


Overlaying Area variable adds additional information

63
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Final Model Build dataset

Rental Rental # Potential Operating Environmental


Price Area Space Visitors hrs Factor
KPKNL
16,281,000 BATAM 36 100 12 0.6
KPKNL
35,542,000 BATAM 20 100 8 0.6
KPKNL
13,680,000 BATAM 36 30 8 0.6
… … … … … …

64
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

MODEL AND VALIDATION


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Exercise: Making Decisions with Data instead

Interpret the following graph

• The X-axis is the “Cause” and the Y-axis the “Effect”

• X-axis = Ice Cream Consumed, Y-axis = Weight Gain


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Statistical Significance: Careful What You Wish For


Satisfying relationship

100

y= 0.58x + 21.21
My Weight Gain

80

60
R-squared = 0.25
Y Axis (Effect)

y=0.58x + 21.21
R−squared=0.25, p=0.02
p = 0.02
40

20

0 20 40 60 80

X Axis (Cause)

City Ice Cream Sales


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Statistical Significance: Careful What You Wish For


Satisfying relationship

100

y= 0.58x + 21.21
My Weight Gain

80

60
R-squared = 0.25
Y Axis (Effect)

y=0.58x + 21.21
R−squared=0.25, p=0.02
p = 0.02
40

20

0 20 40 60 80

X Axis (Cause)

City Ice Cream Sales


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Same Data, Different Conclusion


Larger or Repeated Samples
100

80
My Weight Gain

60
Y Axis (Effect)

40

20

0 20 40 60 80 100

X Axis (Cause)

City Ice Cream Sales


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

How do you make sure you aren’t predicting noise?

• Sufficient sample size


• The predictors “need” to make sense
• Following the assumptions of a statistical test
• Refer to literature and previous studies for
guidance
• Repeated experiments or analyses
• Plot the data
• Hold out data samples
• Be wary or outliers (and removing them)

70
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Predictive Model Process:


Historical Data & Supervised Learning
Variable 1 …. Variable X Annual Rent Build model to predict known
outcome (Annual Rent)
0.1969 132 390 100,000
Machine
… … … … Learning Model
0.5179 173 1150 83,293 Use new data in
previously built ML
Data with known outcomes model to produce
(Annual Rent) predictions

Annual Rent
Variable 1 …. Variable X
(Predicted)
New data without 0.137 390 2
known outcomes 125,000
0.177 23 .5 89,000
0.145 10 9 882,591
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Classification of Major Techniques within Machine Learning

Machine
Learning

Inductive Instance-based Genetic Neural Bayesian


Learning Learning Algorithms Networks Networks

Linear Decision Unsupervised


Models Trees Learning
Supervised Reinforcement
Learning Learning
Supervised Learning

Pham and Afify (2005)


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Common Supervised ML algorithms


Linear Robust
Regression Regression

Linear
Logistic Support vector
Discriminant
Regression machines
analysis

Neural
GLM Decision trees
networks

Boosting Bagging

Random
73 forests
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Model Build Process

74
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Final Model Regression

75
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

FUTURE WORK THEN


DEMO OF PROCESS, DASHBOARD AND
DEPLOYMENT
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Future Work

• Validation and improvement of Models • Additional Data Sources:


• More Historical data
• Additional Variables
• Crime, schools, employers,
• Introduce fields collected by experienced tourists, etc
evaluators
• Sales
• Adjust rent for inflation
• Actual business
• Understand how covid affected rents
• Use of Lats\Longs
• Adjust for inflation
• There are specific geo-location tools to
determine distance to important features • Use the model
• Driving distance
• Satellite images

77
THANK YOU
altair.com

#ONLYFORWARD
©©Altair
AltairEngineering,
Engineering Inc. Proprietary and Confidential. All rights reserved.

1985 13,000+
Founded & Headquartered Customers
in Troy, MI U.S. Globally

$532M 86
FY21 Offices in
Revenue 25 Countries

3,000+ 150+
Engineers, Scientists, Altair and Partner
and Creative Thinkers Software Products

79
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

11,000+ Customers Worldwide


Automotive Aerospace Civil Education Energy Financial
Engineering Services

Government Heavy Industrial Life & Earth Material Technology


& Defense Rail Goods Sciences Suppliers

80
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Extract and Prep Data with Altair® Monarch®


Generate trusted data sets from any source

Universal Data Access


Point and click access to data stored in PDFs,
Microsoft ® Excel® spreadsheets, text files, websites,
JSON, XML, relational databases, big data and cloud
sources, and ECM systems.

Robust Preparation
Turn difficult data into smart data. Dedupe, redact,
generate calculated fields, split/merge, filter, join,
pivot/unpivot. Auditable.

Easy to Use
Built for non-technical users. Click-driven prep with
80+ prebuilt functions. No scripting. No coding.

Automate
Wizard-based approach to building automated tasks
and scheduled, repeatable processes.

Scale
Support any number of users in a governed, secure
environment. Pooling and failover. Cloud-ready.

Extract Augment Visualize Operationalize


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Drag-and-Drop Machine Learning with Altair® Knowledge Studio®


Build trust with interpretable and explainable AI
Visual Model Development
Designed for all skill levels. No coding. Generate
explainable results. Import models built in Python or R.

Patented Decision & Strategy Trees


Decision trees support intuitive, interactive segmentation
and modeling. Strategy trees support prescriptive models
incorporating KPIs and treatment assessments.

Advanced Scorecards
Automate loan applications and similar processes.
Utilize weight of evidence, logistic regression, and
reject inference methods.

Operationalize in Seconds
Upload models to SmartWorks Analytics with one click.
Export Python, R, SQL, SAS Language, or PMML code
to third party systems.

Extract Augment Visualize Operationalize


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

The RapidMiner Platform

One Platform
Data Engineering for Everyone
Connect, acquire, explore, prepare,
catalog and pipeline your data

Model Building
Automated Data Science Create models through automated,
visual, and code-based approaches
Fully automated – upload data, get
predictive insights True Team
Model Ops Transparency
Simplify operations and deploy
models wherever they bring value

Visual Workflow Designer AI App Building


Flexible, visual drag-and-drop designer Make insights easy to consume
with automation using a no-code approach

Collaboration & Governance


Enable sharing and widespread reuse of
RAPIDMINER work without breaking policies and
regulations
Digital
Powerful, accessible, and Enterprise
responsible data science for Agility
all Embedded Coding Notebook Trust & Transparency
Code-centric approach for total Understand and build confidence in
customization predictions across the enterprise
© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

SAS Language Processing with Altair SLC™


Run SAS language programs, models, and workflows without any third-party software

Multi-Language, Multi-Platform Data Engineers DevOps Engineer Business users


Compiles SAS language, SQL, Python, and R code. Works on Data Scientists Third-party users
IBM mainframes, in the cloud, and on servers and workstations
running a wide range of operating systems. Supports remote job
submission and data exchange between mainframe, cloud, and
on-premises installations.
Problem Publish

Access Any Data


Altair SLC can access virtually any data source, including cloud
Altair Analytics Altair SmartWorks Altair SLC Business
services, Hadoop, data warehouses, databases, SAS language, Workbench Hub Applications
SPSS, Microsoft® Excel®, CSV, and other file-based data formats Prep
+ Model & Program Runtime
with no limits on data volumes. Discover Repository
+
Model
+
Create deployment Design Test
code andbuild and
API validate

REST API
Seamless Migration Create API
+ Protocols
Manage models inproduction

Test
Altair’s code analysis tools can analyze thousands of programs in
REST API
minutes. Professional services to support the complete migration
process, including assessment, proof of concept, and rollout.
Deployment
Program Analytics
Code

Extract Augment Visualize Operationalize


© Altair Engineering, Inc. Proprietary and Confidential. All rights reserved.

Make Insightful Decisions with Altair® Panopticon™


Process and visualize massive amounts of fast-changing data
Visualize Any Data
Visualize true real-time streaming data and examine
time series data down to the nanosecond timestamp.

Connect to Any Source


Direct native access to all popular real-time
streaming, time series, SQL, and Big Data sources
with no middleware or custom coding needed.

Drag-and-Drop User Interface


Respond quickly to changing business requirements,
reduce risk and cost, and deploy new applications
and dashboards in minutes.

Enterprise Scalability
Deploy on-prem or in the cloud (AWS, GCP, Azure,
Oracle). Embed dashboards in your own
applications. Control external systems directly
from Panopticon dashboards.

Extract Augment Visualize Operationalize

You might also like