Predictive Simulation & Big Data Analytics ISD Analytics - - PowerPoint PPT Presentation

▶
predictive simulation big data analytics
SMART_READER_LITE
LIVE PREVIEW

Predictive Simulation & Big Data Analytics ISD Analytics - - PowerPoint PPT Presentation

Sep 19, 2023 280 likes •611 views

Predictive Simulation & Big Data Analytics ISD Analytics Predict a better future Overview Simulation can play a vital role in the emerging $billion field of Big Data analytics to support Government policy and business strategy

slide-1
SLIDE 1

Predictive Simulation & Big Data Analytics

“Predict a better future”

ISD Analytics

slide-2
SLIDE 2

Overview

Simulation can play a vital role in the emerging $billion field of Big Data analytics to support Government policy and business strategy decisions Overview

  • How simulation plays a key part in the Big Data Predictive Analytics process
  • Introduce Simulait simulation-based consumer analytics platform

“Predict a better future”

  • Introduce Simulait simulation-based consumer analytics platform
  • Case studies: water, energy, emergence response, retail, transport
  • Simulait Online – simulation in the cloud for on-demand access and large scale

simulations

slide-3
SLIDE 3

Data Analytics & Decision Process

Past Future

Observe

Descriptive Analytics

Predict

Predictive Analytics

Influence

Prescriptive Analytics Business Questions:

What happened?

Business Questions:

What is likely to happen?

Business Questions:

What should I do about it? “Predict a better future” What happened? Why did it happen? What is happening? Why is it happening? What is likely to happen? What should I do about it? How do I influence the future? What are the consequences?

Solutions:

Data mining & forensics Real-time analytics & mining Market segmentation Reporting & dashboards Ad-hoc database queries

Solutions:

Simulation Statistics & linear regression Predictive data-mining Forecasting & trend reporting

Solutions:

Simulation Optimisation

Less data, greater insight, greater value

* Based on Gartner’s model of analytics

slide-4
SLIDE 4

Projection vs Prediction

Traditional statistical approaches project future behaviour by extrapolating past behaviour

  • Observe and forecast what people do but not “why” they do it
  • Unable to effectively represent complex consumer behavior
  • Limited functionality – unable to address a broad range of business problems
  • Past demand is not always a good predictor of the future

“Predict a better future”

2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 10 000 1000 100

Total Sales

Changing population & consumer trends Influence future sales by testing strategies with Simulait 2023

slide-5
SLIDE 5

SimulAIt – An Analogy

SimulAIt is a real life SimCity application where businesses or Government can predict and test strategies to influence the behaviour of large populations

  • Diverse domains: water, energy, emergency response, retail, transport, ...
  • Diverse applications: strategy, policy, pricing, demand forecasting, marketing,

community behaviour and social planning, new product uptake, etc....

  • Global applicability: Australia, Europe, USA
  • Cloud solution: SimulAIt Online can be accessed on-demand using a web browser

“Predict a better future”

slide-6
SLIDE 6

Simulait: A Truly Predictive Approach

  • Accurate: proven approach, demonstrated over 95% accuracy
  • Model not built on past demand data – demand data used to validate the model
  • Accuracy due to greater representation of a broad range of consumer factors
  • Benefits are more than accuracy – it’s the scenarios that you can test with it!!

“Predict a better future”

slide-7
SLIDE 7

Simulait Architecture

“Predict a better future”

slide-8
SLIDE 8

Case Study 1: Victorian Water Utilities

Objectives

  • Isolate and quantify the effectiveness of past water conservation strategies – economic,

regulatory, social (communications) & environmental

  • Forecast bounce-back in water demand from easing restrictions & price increases
  • Assess impact of product uptake on demand and revenue

“Predict a better future”

  • Assess impact of product uptake on demand and revenue
  • Build a business case to industry regulators – pricing review
  • Build demographic demand profiles
  • Blind validation: Used 4 yrs of demand data to calibrate outdoor water use and then

forecast next 6 years of demand without access to actual demand data

slide-9
SLIDE 9

25 30 35

umption

Average monthly household water consumption

Case Study 1: Victorian Water Utilities

Blind validation results

“Predict a better future”

5 10 15 20

Jul-00 Jul-01 Jul-02 Jul-03 Jul-04 Jul-05 Jul-06 Jul-07 Jul-08 Jul-09 Jul-10 Water consump

Simulated Actual-calibration data Actual - blind validation data

slide-10
SLIDE 10

Case Study 1: Victorian Water Utilities

Key outcomes and benefits

  • Informed capital expenditure, corporate plans, water restriction schedules
  • Rigorous business case to industry regulators to maximise product price and

revenue

“Predict a better future”

  • Isolated and quantified the effectiveness of past & future strategies (campaign

analysis)

  • Informed & increased ROI on future strategies
slide-11
SLIDE 11

Case Study 2: Water in USA & France

Key outcomes and benefits

  • Model transferable to different countries
  • Better for long term forecasting – tendering, strategic & financial planning, design

future cities, etc...

  • Support water conservation, regulation, new water rates, impact of recession, etc...

Calibration “Predict a better future” >90% Accuracy Calibration point

slide-12
SLIDE 12

Case Study 3: Rebates/Retail

Objective

  • Identify a mix of products and prices for the water rebates program that maximises

efficiency and keeps within the program budget

  • Three projects, and now a 3 year license to 2015

Approach

  • Simulated 2 million households, 4.5 million consumers
  • Incorporated consumer preference and affordability, and product age, failure and

“Predict a better future”

  • Incorporated consumer preference and affordability, and product age, failure and

price

  • Simulated product uptake and efficiency with different prices

Key outcomes and benefits

  • Accurate predictions of product up-take and budget spend
  • Prevented budgets blow-outs
  • Cost/benefit (triple bottom line) analysis of different strategies
  • Forecast the ROI of different demographics and regions, and to assist with targeted

(micro)-marketing of the rebate program

slide-13
SLIDE 13

Case Study 4: Energy Customer Personalization

Energy load forecasting accuracy

Total Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec 2008

99.0%

99.2% 97.9% 98.8% 98.0% 95.0% 98.5% 99.6% 97.0% 99.6% 98.7% 96.5% 85.0%

2009

99.8%

96.7% 99.3% 99.3% 99.0% 98.9% 98.4% 98.8% 95.1% 97.3% 93.1% 98.6% 98.3%

Using 1% of CRM data in the first 6 months, Simulait was able to accurately predict what each specific customer will do, and why, for the next 2 years!!!

“Predict a better future” 2009

99.8%

96.7% 99.3% 99.3% 99.0% 98.9% 98.4% 98.8% 95.1% 97.3% 93.1% 98.6% 98.3%

2010

98.3%

91.9% 97.9% 97.1% 97.6% 98.6% 98.1% 99.1% 97.1% 87.8%

50 00 50 00 50 00 50 00

Actual Forecast

Calibration Prediction

slide-14
SLIDE 14

Case Study 5: Energy - EV Uptake & Transport

Objective

  • Predict the uptake of Electric Vehicles over time to 2040
  • Predict usage and charging behaviour of electric vehicles
  • Impact on the electricity network (extra peak load) to support reliability and quality

risk management

“Predict a better future”

slide-15
SLIDE 15

Case Study 5: Energy - EV Uptake & Transport

Approach

  • EV Uptake consumer decision model
  • Simulated the new and used vehicle market across Australia
  • Considers many dynamic factors: consumer type, petrol and elec price, car

range, charge times, charge infrastructure, upfront price, ongoing costs, dwelling suitability, battery replacement, depreciation, market penetration, etc...

  • EV usage: transport/activity model

“Predict a better future”

  • Model each consumer’s daily activities and transport/vehicle use
  • Factors include: consumer type (e.g. occupation, family structure), day of week,

number of vehicles in the household, activity types (work, school, shopping, entertainment, family/social visits, etc...)

  • Other factors: passenger trips, infant trips to carers if both parents working,

separate household activities for independents, vacation from work (e.g. for parents during school holidays), etc...

  • EV charging and increase in peak demand
  • Charge times and location: home, work, fuel station, shopping centre, etc..
  • Other complex factors: power point upgrades, vehicle-to-grid system
slide-16
SLIDE 16

Case Study 6: Emergency response - bushfire

Following the 2009 bushfires that claimed 173 lives, the Victorian Royal Commission identified that “...strategies must reflect how people actually behave... Timely and accurate warnings can provide triggers, but the content and delivery must be carefully developed to elicit the right response”

“Predict a better future”

slide-17
SLIDE 17

Case Study 6: Emergency response - bushfire

Objective

  • Model community behaviour to bushfires and warnings to support bushfire

strategy and policy, and ultimately save lives

  • The model predicts:
  • What people do and when: Stay, leave or “wait and see”
  • Where will people go: neighbours, designated shelter, leave region, open area

“Predict a better future”

slide-18
SLIDE 18

Case Study 6: Emergency response - bushfire

Approach

  • Based on a health model of behaviour change – individual’s life is at risk
  • Potential to be applied to support health policy and manage the unsustainably

increasing health costs

  • Given where people are, who they are, what they are observing, the

warnings they are receiving (and which mediums, e.g. radio, text, etc.), and the progression of the bushfire, we determine the level of threat,

“Predict a better future”

the progression of the bushfire, we determine the level of threat, vulnerability and uncertainty for each individual/family, and thus response

Wait

Perceived Threat Perceived Vulnerability

Level of motivation to act Wait Wait Wait Wait Wait Leave Stay Decision threshold Decision threshold

slide-19
SLIDE 19

Case Study 6: Emergency response - bushfire

Validation & outcomes

  • Applied the model to two bushfires in Victoria and South Australia and

demonstrated >90% accuracy

  • Currently assessing hypothetical bushfire scenarios to support bushfire

policy and strategy

  • Can be applied in emergency response situations beyond bushfires...

“Predict a better future”

  • Can be applied in emergency response situations beyond bushfires...
slide-20
SLIDE 20

SimulAIt Online (SOL)

  • Access SimulAIt via a web browser
  • SimulAIt Online allows:
  • Access validated models online
  • Add many users
  • Create multiple scenarios – test assumptions and what-if analysis
  • Share scenarios (models), results, notes and descriptions
  • Refresh data and configure assumptions, parameters, etc...

“Predict a better future”

  • Refresh data and configure assumptions, parameters, etc...
  • Run simulations
  • Download results – disaggregated via region and time or other factor
  • Benefits
  • On-demand access to models, for technical and non-technical users
  • Control, visibility, ease of use
  • Facilitates collaboration and consistency: share scenarios and results
  • Maximise ROI: execute many scenarios when required
  • Hosted solution: no installation of software or hardware required to run large

scale simulations

slide-21
SLIDE 21

Case Study 7: Vic ESC & Retailers

Challenge

  • Limited availability of suitable data and forecasting models presents a

challenge for regional water retailers to produce accurate forecasts for their pricing review

Approach

“Predict a better future”

Approach

  • Team members collaboratively used SOL to create validated models with

minimal data

Key outcomes and benefits

  • SOL enabled team members to access, configure, validate, and share

models and forecast results

  • Demand forecasts were used to support their pricing review
slide-22
SLIDE 22

Summary

  • Simulation can add significant value to support strategic decision making

and policy for Government and business

  • Unique and important role to play in “Big Data”
  • Provide the “right” information to make better decisions: predict and

how to influence

  • Simulait is a practical approach for problems involving consumers and

populations: i.e. human behaviour

“Predict a better future”

populations: i.e. human behaviour

  • High level of accuracy and functionality
  • Demonstrated in various domains and countries with minimal

configuration

  • Simulait Online web/cloud based solution provides on demand access for

users globally

  • Collaborative tool: access, share, run scenarios, and download results
  • Access to “limitless” computing power to run large scale scenarios
slide-23
SLIDE 23

ISD Analytics

Questions?

“Predict a better future”

ISD Analytics

27 Chesser Street, Adelaide, South Australia, 5000 Phone: +61 8 7200 3589 info@isdanalytics.com

  • www. isdanalytics.com
slide-24
SLIDE 24

SOL Technical Overview

SimulAIt Online (SOL)

Web User Interface Users

  • Configure scenarios
  • View/compare results

SimulAIt Hosting Centre

Scenarios & Results CPU On Demand

Internet

SOL Server Application

“Predict a better future”

Dynamic Multi- Dimensional Database

Models SimulAIt Micro-Simulation Engine

Population Dynamics

Models Models Domain Specific Models

(water, energy, retail, finance, ...)

SimulAIt Platform and Models (SPM)

Census Data New/Updated Models

Data utilised:

  • Market research &

social data

  • Econometric &

statistical data

  • Engineering and

environmental data

  • Customer data

(billing, purchases....) & Results Rules, behaviors, logic, reasoning, ...

slide-25
SLIDE 25

Main SOL screen

Scenario groups Model type User & logout Scenario menu items Admin menu items Session message Session messages

“Predict a better future”

groups Scenarios Working pane message log Active scenario

slide-26
SLIDE 26

Scenario: Configuration

Parameters tree: hierarchical Config input type Time associated with parameter values

“Predict a better future”

hierarchical to reduce complexity Time explicit parameter values (cells) Slide to increase working pane Scroll cells through time

slide-27
SLIDE 27

Run scenario – SimulAIt!

Start simulating the scenario

“Predict a better future”

Set the scenario start and end times Region tree Save the selected regions for the scenario Selected regions

slide-28
SLIDE 28

Scenario: Results

Range of results to download: Water, energy, carbon, revenue, etc. “Predict a better future” Monthly, yearly Disaggregated into different regions, appliances

slide-29
SLIDE 29

Outputs: Monthly Demand

“Predict a better future”

slide-30
SLIDE 30

Outputs: Yearly Demand

“Predict a better future”

slide-31
SLIDE 31

Outputs: Household Usage

“Predict a better future”