• glossary
  • big-data
  • data-analysis
  • design-thinking
  • q-and-a
  • case-studies

Glossary of Terms

Analytical Services

Trend Analysis

Identifies opportunities by fitting the best trend line to a set of data over time.

Experimentation

Identifies the most statistically significant factors and quantifies their contribution and the contribution of a combination of factors to the response or desired output.

System Engineering

A hierarchical model describing the decomposition of requirements from the high level customer to the product’s or service’s measurable characteristics. The model also verifies each characteristics contribution to the customer.

Production Capability Assessments

Assessment of process stability and performance over time.

Measurement System Analysis

Quantifies the contribution of the measurement system to process variation. A measurement system is often comprised of several inputs (human, equipment and methods). In percentage terms, if the measurement error is low at 10%, the process variation is 90%.

Process Flow Mapping

Graphical representation of process yield or output underpinned by statistical analysis. Identifies opportunities for improvement.

Big Data - Artificial Intelligence

Big Data Science which generates complex predictor models for products & services. AI is typically based on continual analysis of data generated from connected multiple devices.

Competitive Benchmarking

Compares products or services and identifies opportunities to commonise, differentiate, simplify or diversify a product, service or portfolio. Analytic Techniques range from simple to sophisticated.

Problem Solving

A suite of structured techniques which identify and verify the root cause of a problem to create opportunities for improvement. It is an input to idea creation and development.

Failure Mode Avoidance

Actions & countermeasures to avoid or minimise the likelihood of failures to ensure products and services are robust to external noise factors. Failure Mode Avoidance requires a good understanding of the signal state or desired function. Each failure mode has a severity & an occurrence rating.

Warranty Analysis

Quantifies the failure rate and predicts the cost of warranty or customer complaints over time periods.

Regression Analyses

A best fit equation that describes the relationship between one or more predictors and the response variable and includes the statistical confidence intervals for fit.

Big Data - Machine Learning

Repeat application of one or more algorithms or mathematical distributions to a large dataset to identify relationships between predictors and the desired output. Highlights opportunities to improve within constraints of the dataset.

Data Visualisation

Graphical presentation of results, often presented in a Dashboard format.

Innovation & Design Services

Customer Profiling

A description of a customer or a cohort (group of customers) that includes demographic, geographic, and psychological characteristics, as well as buying patterns, creditworthiness, and purchase history.

Idea Creation Techniques

Facilitated section of the collaborative workshop dedicated to idea creation techniques. Techniques will be tailored to the client’s needs based on Data Driven Scorecard and follow up consultation. The outcome is a list of ideas.

Idea Development

Facilitated section of the collaborative workshop dedicated to idea development and harvesting techniques. The outcome is a much larger prioritised list of the highest value ideas ready for Experimentation.

Survey & Questionnaire Design

Customised survey creation following analysis of your customers and your business metrics.

Market Segmentation

The process of dividing a market of potential customers into groups, or segments, based on different characteristics.

Idea Evaluation Techniques

Facilitated section of the collaborative workshop dedicated to idea evaluation techniques. The outcome is a list of the high value ideas.

Idea Databasing

The act of creating a database.

Engineering Services

Project Management

The practice of initiating, planning, executing, controlling, and completing the work of a team to achieve specific goals and meet specific success criteria at the specified time. The primary focus of 1iDEA is to manage prototype manufacture to support Experimentation.

Requirement Management

The record and relationship between requirements set at different levels supporting the System Engineering V Model.

Production Problem Solving

Application of Six Sigma DMAIC & DCOV techniques to Production or Process to improve Internal Process Capability and Efficiency.

Specification Formats

Records & Formats describing the purpose of requirements, test procedures and criteria and Reports showing the results of testing.

System Performance Characterisation

Application of Analytical Tools to identify the critical factors affecting system performance.

Business Models

Transfer Functions

Simple and complex predictive model describing the change in response or output due to the changes in one or more proven predictive factors.

Regression Models

Application of statistical regression analysis to create a customised business model equation.

Dashboards

Graphical presentation of a Business’s Key Performance Indicators.

Big Data

For analysis, you need data. Data is everywhere. Data is prevalent in our daily lives. 

We live in such a data rich society as the internet of things has grown into our lives. Our behaviours are defined by data – payments, navigation, online activity, etc.

Data is not something we can really escape from. Data is only going to become more abundant. There are business opportunities in the universe of data. The people and companies who embrace data are the ones that will succeed.

However, in the eyes of many, Big Data is complete chaos and is overwhelming.

Big Data Analysis is providing a huge helping hand at better understanding the customers we have and those we could have. Machine learning and artificial intelligence quickly automate analysis to show correlations and relationships within the dataset that created the models. The opportunities were already there, the analysis has simply exposed them to us. However, each correlation needs validation to prove the relationship between causes and the outcomes works with new data. There are quick wins but for the myriad of correlations, prioritising those of greatest benefit can also result in excessive resource allocation for any business.

Simply, there are two types of data. Qualitative data tends to be subjective, rich in verbatim with small samples. If there is sufficient qualitative data, it becomes quantitative data, hence more useful to study trends, patterns, groupings & clustering.

If you are not embracing the potential of data in business, you are not exploring all potential opportunities. Not all data that is accessible is useful. There is a lot of noise out there. Noise is unwanted variables that negatively influence your outcome and are often outside of your control such as legislation, the economy, politics and society in general.

The art of big data analysis is knowing what is useful and what is noise. Just because there is a correlation, it does not mean there is a causal relationship. Correlations still need to be explained and proven or verified to ensure the control factors in the statistical models are robust and unaffected by the unwanted noise factors. A robust product and business model will minimise the effects of noise;

“Supervised Analysis” makes assumptions about known variables within a field or industry to provide an equation that is strong enough to offset the noise. Then the control factors can be adjusted to positively affect the output. Supervised Analysis is giving way to Unsupervised Analysis based on the simultaneous and rapid application of many equations as part of a program containing many algorithms. This is called machine learning and Artificial Intelligence. Both Supervised and Unsupervised Learning is based on the same pioneering mathematical research conducted in the 1970’s and 1980’s.

Data Science requires Industry Expertise to prioritise & develop the list of business opportunities.

Data Scientist + Industry Expertise = Lots of Opportunities

5 Steps of Data Analysis

Data in Business is getting bigger & faster. Many companies are promoting Machine Learning & AI as answers. So, what is Big Data, should we really be concerned if we don’t jump on the Big Data bandwagon?

Where there is a sale, there is a transaction. Where there is a transaction there is customer data. Are you leveraging the data you have?
Below are 5 levels of data and analyses from simple to complex.

1. Databasing (Immediate Action)

If transactions are recorded offline, build a simple database. Do it now.

2. Fundamental Analysis

The aim of Fundamental Analysis is to identify customer groups and how they behave over time:

  • Using customer profiling to identify your Target Customers.
  • By splitting the data into different customer profiles over time you can see trends and identify emerging customer groups and declining customer groups.

3. Basic Analysis (Data Analysis)

Basic Analysis builds on the fundamental analysis by plotting key events over the time period to provide an indication of possible causes and effects. Some examples of Causes and Effects are:

  • Climatic seasonality through summer to winter.
  • Marketing Incentives.
  • Key dates such as Public Holidays, Grand Finals, School Holidays, Valentine’s Day, Birthdays, Local or National Events in your industry, Times of Day.
  • Recurring and Repeat Purchases can be the result of your product or service since it will wear out or be required again in the future.

Basic Analysis will often result in further questions, requiring further investigation such as collecting more information from your customers by speaking directly or distributing well written efficient surveys.

4. Intermediate Analysis (Data Analysis)

Intermediate Analysis requires some statistical knowledge & skill to ensure there are no false positives or compounding causes. The outcome can be a strategic plan for advertising, incentives, product upgrade or portfolio diversification. Intermediate analysis includes:

Correlations between an independent variable (often presented on the horizontal X-axis) and the dependent variable (often presented on the vertical Y-axis).

Transfer Functions which identify the significance of several factors operating simultaneously that are driving your desired outcome (sales volumes, revenue, engagement rates, conversions, etc). Transfer Functions can be applied to a single product or a portfolio.

5. Expert Analysis (Data Science)

Data Science can be characterized by:

  • Including multiple variables with irregular correlations.
  • A large number of customers and a large portfolio of products or services with multiple variables over a longer period of time (commodity types, prices, appearance, usability, etc).
  • Experimentation is a statistical technique best applied to prototypes which quantifies the contribution and sensitivity of each factor and combination of factors to the desired outcome.
  • Machine Learning & AI.

Should we really be concerned if we don’t jump on the Big Data bandwagon? The answer you can judge for yourself depending on the level of data and analysis applicable to your business now and in the future.

Design Thinking

Design is a noun and a verb. Design is not just an attribute. Design is a strategy. Design is a process and innovation is part of the Design Process.

The Design Process starts with Design Thinking. It’s your customers who we are designing for. Your customers are still the greatest source of business opportunity.

Each opportunity needs a suitable idea that can be quickly and accurately conveyed, manufactured and then converted into commercial value as a product or service for the benefit of a larger population.

Design Thinking techniques can also be used to creatively solve problems. Since a ‘problem’ reflects an existing product or system’s failure to meet user’s needs or expectations, Design Thinking turns problems into opportunities.

Qualified & experienced Designers practice Design Thinking.
Design Thinking is not Design Doing.

Data Driven Innovation

Analysis of existing data could be considered continuous improvement or incremental innovation. Exposing opportunities using Machine Learning & Artificial Intelligence might make a big difference to your business by adding all the small gains; it might make you more competitive or even a market leader. However, the opportunities were already there. The analysis has now brought them to your attention. 

Analysis can also stimulate creativity by extrapolating the equation to see what the solutions look like outside the limits of the data that created the model. 

Step Change or Radical Innovation still requires Out-of-the-box Design Thinking to introduce something new and change the game. 

1iDEA’s Philosophy is based on the following formula.

Data Science + Design Thinking + Industry Expertise = Game Changing Opportunities

Q&A

The fact that you are reaching out shows that you regard Innovation and Design Thinking as important to your future success. 1iDEA recognises that existing companies, however big or small, however old or young, have a history, a culture that is a direct reflection of the founder(s). We respect your culture and work with your team to subtly inject only the essential mindset tweaks, effective tools & techniques, to achieve sustainable positive language, and over time, behaviour and, hence, results.
1iDEA is with you all the way through the process.

The customer is the end user or the next user of your product or service and depends where your business is located in the value chain or supply process; information, raw material, wholesaler or retailer. You are often also a customer to somebody else’s supply. Therefore, each entity has an important role to maintain the overall quality through the value chain.

The tools and techniques applied depend on the phase of the IDEA process. For example:

Idea Creation requires stimuli which can come from a variety of in-house and/or completely different external sources.

Idea development is a phase of the design process that is often not given enough attention and it is here that the cross-fertilisation of initial seed ideas can be very powerful and yield superior solutions.

The purpose of Testing Prototypes is to ensure that your proposed solution meets your customers’ expectations and legal requirements before you commit large funds to production. Testing often highlights problems. The problems are opportunities to improve. The problems may be hard failures, e.g. a part breaks, or soft failures, e.g. a degradation of performance, or simply, an annoyance. 1iDEA coaches the use of structured problem-solving techniques to identify the root causes, temporary & permanent fixes to ensure all production units meets customer expectations and avoid or minimises failures.

1iDEA uses a spectrum of statistical tools from spreadsheets for initial assessment to sophisticated industry leading statistics packages to analyse large data sets.

As company owners you have come to 1iDEA because you feel & think that there is a problem or that you want to explore opportunities to expand your business or improve business efficiency.

We believe that there are solid reasons behind your concerns. Maybe you can’t put your finger on them. 1iDEA will quantify them and while doing so, using the power of statistics, uncover opportunities with statistical confidence.

It depends on the quality of data available. If the data is obtained in a robust reliable manner and the variables or factors being considered are few & simple, then a few dozen samples can yield very useful insights and recommendations. The analysis would be very quick.

If you have a portfolio of similar products or services being distributed and used in different parts of the country (or world) by different customers, we would expect tens of thousands of pieces of customer and product data which can be mined and analysed to yield amazing insights and opportunities that otherwise would not have so clearly been seen. This is big data. The power of statistics breaks it down, identifies themes and quantifies the outputs with mathematical confidence, so you do not have to rely just your gut feel.

If the data is not collected so robustly, 1iDEA can advise how to improve the collection methods and Project Manage the implementation of improved processes.

We believe that business owners are in the business because they already have the necessary specialist knowledge and are producing or about to produce something. 1iDEA can apply a lean engineering methodology to the business with a fresh set of eyes to see if there are any opportunities to improve. 1iDEA can apply & coach the use of FMEA and Statistical Engineering Tools if you wish to engage our skills.

The reward is the satisfaction of seeing businesses improve as a direct result of our collaboration.

1iDEA creates opportunity from apparent chaos using statistics. Sophisticated statistical modelling often reduces to simple equations. Statistics can show you not only the few simple variables or factors contributing to the success of your business but can also quantify the relationship between the variables.

Sometimes, the relationship between two factors is more powerful than each individual factor alone. Changing the value of one factor may have a positive or negative compounding effect on the other and hence on the overall outcome. Tuning the factors appropriately within a range can give you the competitive edge or it can show you your maximum potential within given constraints.

1iDEA can show you the key reasons why people buy your products or services and help you pull those levers to maximise your outcome.

That knowledge is worth sharing.

1iDEA’s founder has worked in the Automotive Industry since 1995 with healthy periods in white space vehicle innovation & concept creation including market research & consumer insights, design & engineering, quality assurance, prototyping & testing through final production & manufacturing and measuring process capability.

The motorcar is the second most costly product purchase for most people and is arguably the most complex product that individuals own. Compared to its first conception in the late 19th Century, the humble motor vehicle now has many functions, attributes, customers and expectations.

The quantity of data collected by the motor vehicle itself and automotive industry is huge and diverse. Statistics have been and are used throughout the automotive development cycle to support executive level decision making to positively increase customer satisfaction and sales.

Case Studies

Below are some simplified Case Studies demonstrating the application of Data Analysis to different business scenarios and the opportunities that it creates.

Each case study contains questions or hypotheses, methodology, an introduction and explanation of some basic statistical terms and techniques, supporting graphics, application of the predictive model, recommendations for future business strategies.

Scroll to Top