You’re going to need a bigger boat!


With the recent 42nd anniversary of ‘Jaws’ the film, everyone always comes up with the tagline above ‘you’re going to need a bigger boat’ and that led me recently to consider where we have come from regarding engineering, calculations (to solve problems), data, data science and now to Big Data, the Internet of Things (IoT) and its Industrial counterpart and the role of the engineer and the data scientist.

Back in my day, not quite 42 years ago (but close), we did calculations by hand, on paper, with a calculator, often requiring engineering ‘iterations’ to get the right design flow (or whatever). Yes, we made mistakes (probably too many to worry about!) – then we had spreadsheets (to speed up iterations with less mistakes), then static process simulations to speed up the design and test alternatives, then dynamic process simulations to allow us to ‘predict’ the performance of the plant so as to help optimize the design – from there integrating with controls systems to develop control room operator training and from there to 3D Virtual Reality headsets that allow the User to ‘walk’ around the plant integrating control room and field operations etc….

And so into predictive analytics, where engineering meets data science…Predictive analytics has been around for quite some time and the ‘engineering’ approach has been to seek the answer to the question that everyone asks after there has been some kind of process or equipment failure, outage or worse still some kind of accident ‘Why couldn’t we see this problem coming?’ and usually, you can, but you have to be looking at all the variables, all the time and apply your engineering knowledge and skills to ‘spot the problem’ way in advance.

Clearly, you can apply lots of engineers and operators to look at all the data all of the time or you can use computer software to help. Early solutions involved looking at the ‘time series’ data only, as deviations from the ‘normal’ are relatively easy to spot and ‘trending’ solutions can alert and notify the host. But, as referring to my earlier engineering statements, users then want more – from spreadsheets to 3D VR – once you have your predictions based on time series analytics – then you want to add context, add CMMS and Maintenance data, operation logs, does the weather play a part, etc… and by adding each level of complexity, then the ‘problem’ to be solved gets much more complex and your ‘time series’ algorithm, even if it’s a really good one, just doesn’t stack up.

So you need to look at the problem from different aspects and try to find the best way to solve the ‘really big’ problem – which is – ‘How do I take all my relevant data – format it in a way that it can make sense and then contextualize it in a way that I can begin to make sense of it and then use all that data to ‘predict’ whats going to happen’. That’s a big problem that will need a big computer (‘gonna need a bigger computer’) and complex algorithm(s) to solve it.

Cloud computing has been around awhile, as has ETL (Extract Transform Load), and that is what impressed me so much to join Predikto, their ability to take all the data (as much as anyone would need or want), ETL it, put it in the Cloud, allow our ‘MAX’ Predictive engine to chew through it (just once, for 3-4 weeks), and then begin to apply every known algorithm that every Data Scientist might know (and a few of our own) AND, daily, optimize those algorithms for accuracy, applicability, and optimize for the types of features that help the predictions depending on the varying conditions of the process or asset (or weather etc) that are affecting it daily, hourly, etc….

Now that is really, REALLY clever stuff….and things that our customers have been asking for, for over 25 years in the business….

Big Data, IIoT, Industrie 4.0 and all the things that bring these together combined with what we are doing with Predikto – now that’s the future…..and I am honored to be part of Mario and Robert’s team – watch this space – stay on this track (sic), the future is in Predikto and is HERE!

By Paul Seccombe.

Paul joined Predikto in 2017 after his role as Solutions Leader at the GE Predix Oil & Gas for Europe and the Middle East. He was also at Smart Signal for many years. Paul holds a PhD in BioChemical Engineering from the University of Wales. He is based out of London.

Digital Transformations : From Analysis Paralysis to Execution Mode

Digital Trans

I have never been more excited about the future of Predikto. We started 4 yrs ago with the Vision of “Moving Unplanned to Planned”. We wanted to help large industrials “To harness the power of predictive analytics to optimize operational performance”. We are enabling this with:

  1. Our software platform including Predikto MAX which automates machine learning algorithm generation at a massive scale
  2. Our unique approach to data preparation optimized for Machine Learning

So why am I so excited? We have seen a big shift in the past 12 months of organizations going from “analysis paralysis” to “let’s start to execute”. We love it when prospects get what we have built. This was not the case 3 and 4 yrs ago. It takes a sophisticated organization to be ready to capitalize on our technology. We look for:

Clear Strategy

A clear strategy with the Executive support that incorporates AI, Predictive Analytics, Analytics/Digital Transformations, and investments that will enable them to increase revenues or cut costs by leveraging their own data. A recent report by IDC found that 80% of senior executives said investing in digital transformation is critical to future success. Investments in digital transformation initiatives will reach USD2.2 trillion by 2019 which is 60% more than this year.

Organizational Readiness

Organizational readiness is another key aspect of prospects and customers who are ready for our technology. Most customers have hired a Chief Digital Officer who came from the outside to change the way they have tackled innovation and digital transformations. They have dedicated teams with the power and budgets to run multiple pilots with companies big and small to learn how new technology can bring tangible value to their organization. They are learning to move fast and fail fast. The best ones are learning from startups and aligning their key initiatives with true disruptors. If you are looking for Ginni to sell you IBM Watson to solve all your problems, you are going to have a rude awakening in 18 months. We actually look for prospects who have already hired IBM and failed. IBM, please send me your list of Pilot customers from the past 3 years for Predictive Maintenance projects.

Technical Transformation

Technical transformation means a lot of different things depending on the industry vertical. Some customers did not have access to their own equipment sensor data since the OEM would keep it. They had to invest in new hardware to tap into the sensor data inside trains. Others had data stored in siloed on-prem historians and it was a challenge to get their IT Security organization to push that data to the Cloud. Others are trying to figure out which cloud provider to go with? If you are still wondering, there are only two you should consider, AWS and Microsoft Azure.

We are finding that prospects that are moving and executing have figured out all three components of their Digital Transformation. IDC also states that by 2019, 40% of All Digital Transformation initiatives, and 100% of all effective IoT efforts, will be supported by Cognitive/AI capabilities. I am excited about our future and the AI / Machine Learning software we have built to bring value to large industrial transportation companies looking to move from Unplanned to Planned using a data approach to complement their engineering based condition monitoring approach.

Predikto is featured in ARC Advanced Analytics and Machine Learning Guide

Predikto has been featured in the latest “Advanced Analytics and Machine Learning Planning Guide” by ARC.  Predikto is a powerful and innovative technology that helps asset-intensive industrial customers to deploy advanced analytics and machine learning algorithms to predict failures in their equipment.

Founded in 1986, ARC Advisory Group is the leading technology research and advisory firm for industry, infrastructure, and cities. ARC stands apart due to our in-depth coverage of both information technologies (IT) and operational technologies (OT) and associated business trends.

The Planning Guide is designed to help organizations navigate the buying process for advanced analytics.

With an emphasis on predictive solutions, cognitive intelligence, and machine learning, this planning guide will provide useful ways of thinking about analytics. It will clarify the different analytics modes, from the enterprise to the edge. The report will:

  • Explain key concepts needed to navigate the buying process
  • Help you understand how to select a solution that fits your business
  • Detail recent market entrants
  • Provide insight into how traditional technology providers with analytics are positioned in the market
  • Build Business Case Consensus

Predikto Named by Gartner as a Cool Vendor in IoT Analytics


Predikto has been included in the “Cool Vendors in IoT Analytics, 2017” report by Gartner, Inc.

It is an honor to be included in the Gartner Cool Vendor report. This recognition is validation on our ability to bring machine learning algorithm development software at a massive scale to help improve equipment uptime. By automating close to 80% of the process of creating machine learning algorithms, we are able to empower our customers to complement existing condition maintenance rules based systems with the power of machine learning on a massive scale. Our approach includes Predikto Maintain, a software that bridges the gap between machine learning algorithm output and the information required by Maintenance and Reliability Engineers to do their job more effectively and reduce unplanned breakdowns.

The Gartner report “Cool Vendors in IoT Analytics,” by analysts Svetlana Sicular, Jim Hare, Saniye Burcu Alaybeyi, Shubhangi Vashisth, and Simon F Jacobson was published April 27, 2017.

Gartner Disclaimer
Gartner does not endorse any vendor, product or service depicted in our research publications, and does not advise technology users to select only those vendors with the highest ratings or other designation. Gartner research publications consist of the opinions of Gartner’s research organization and should not be construed as statements of fact. Gartner disclaims all warranties, expressed or implied, with respect to this research, including any warranties of merchantability or fitness for a particular purpose.

For additional information or a product demonstration
Please contact us at

Predikto closes $4 Million investment – adds Jim Gagnard to BOD

Last month we announced a $4m VC led round to help us expand.  This latest round was led by Fidelis Capital and our prior investors, TechOperators, also participated in the round.  We also added Jim Gagnard, ex-CEO of Smart Signal (acquired by GE) into our BOD as our latest independent board member.  Investors in this last round also included a strategic with deep expertise in Aerospace and Defense globally.

Looking back at our 4-year history, I would like to take this opportunity to reflect on our past, paint a picture of where we are today, and explain the road ahead for Predikto.

We started with the idea that automated insights from large amounts of industrial equipment data could disrupt how maintenance, operations, logistics, PLM, and after market capabilities for large industrial players.  Organizations spend millions adding sensors, improving business processes, deploying software to improve how businesses are run, but in the end, humans are heavily required to extract insights from data.  With the explosion of new sensors and IoT, more data means more challenges in gaining actionable insights from that data.  Our focus and goal is to try and “automate” machine learning and predictive analytics algorithm development as much as possible to provide targeted solutions to problems faced by our customers.  If we could automatically create lemonade from lemons, we were onto something big.  We raised our first $3.6m of funding in December of 2014.  This enabled us to expand our core team which primarily included Robert, Will and me.  We were able to bring in the right talent with expertise who had scars building large scale complex cloud-based software applications (Roy joined to lead our Engineering team).  We also invested in Sales & Marketing at that time.  We were going to market with a wide net and chasing anything that moved.  After gaining a deeper understanding of our market, customers and how they “do business”, we felt it was critical for us to focus in one vertical and then expand from there.

About 18 months ago we decided to focus in Rail.  We had some early customers and a lot of new opportunities in Rail globally.  We also had a few channel partners who would help us expand in the rail vertical.  We hired 4 team members who came from Rail and this brought credibility, expertise, and a much deeper understanding of our customers and prospects that we lacked from the start (Greg joined to lead of Services / Solutions team).  Our success enabled us to expand our use cases, experience, and gain more scars.  Our success made it possible to begin to expand beyond Rail and open up the dialog with prospects in Aviation, Shipping, and now Wind Turbines.  We invested heavily in productizing and improving the Predikto Enterprise Platform for fast data ingestion and ETL.  We also continued to invest in automating and expanding the capabilities of Predikto MAX.  This has made it possible to do more with less (people and time).  In the last 6 months, we have been focusing on the latest release of Predikto Maintain which we believe is a huge step forward in helping asset-intensive organizations to operationalize in the real world how a maintenance engineer would translate the predictive output from very advanced and sophisticated machine learning algorithms into maintenance notifications or actionable warnings.  The context and supporting information provided by the Predikto Maintain application is critical in helping a Maintenance Engineer feel comfortable and answer the questions to:

 – Why should I believe this Predikto MAX prediction that my motor is going to fail?
 – How much time do I have until the asset or component is most likely to fail?
 – What are the risk and business impacts of my action (or lack of action)?

Today, we are expanding in multiple accounts globally across Freight Rail, Commuter Rail, Shipping (terminals), and Aviation.  Our platform and messaging are working. The space is still trying to sift through all the cluttered messaging from big and small competitors.  Our approach is to let our results speak for themselves.

So now what? This latest round of funding is to expand the team to ensure the current customer expansions and deployments go well.  We have a backlog of work and deployments for the year that is forcing us to continue investing in our software to ensure partners and customers can expand the deployment of Predikto software on their own.  We are also expanding into Azure later this year due to pressure from customers (we are in AWS EU and North America today).  Our team is solid and we continue to add key resources on a monthly basis.  I am proud of what we are doing and the direction we are going.  We are landing new huge customers who are leaders in their space.  They have invested in Data Science and advanced analytics, and they feel they need our help to get to the next phase in improving asset uptime with our analytics capabilities.


The Missing Link in Why You’re Not Getting Value From Your Data Science

The Missing Link in Why You’re Not Getting Value From Your Data Science

by Robert Morris, Ph.D.

DECEMBER 28, 2016

Recently, Kalyan Veeramachaneni of MIT published an insightful monologue in the Harvard Business Review entitled “Why You’re Not Getting Value from Your Data Science. The author argued that bfbusinesses struggle to see value from machine learning/data science solutions because most machine learning experts tend not to build and design models around business value. Rather, machine learning models are built around nuanced tuning and subtle, yet complex, performance enhancements. Further, experts tend to make broad assumptions about the data that will be used in such models (e.g., consistent and clean data sources). With these arguments, I couldn’t agree more.



At Predikto, I have overseen many deployments of our automated predictive analytics software within many Industrial IoT (IIoT) verticals, including the Transportation industry. In many cases, our initial presence at a customer is in part due to limited short-term value gained from an internal (or consulting) human driven data science effort where the focus had been on just what Kalyan mentioned; a focus on the “model” rather than how to actually get business value from the results. Many companies aren’t seeing a return on their investment in human driven data science.

wallThere are many reasons why experts don’t cook business objectives into their analytics from the outset. This is largely due to a disjunction between academic expertise, habit, and operations management (not to mention the immense diversity of focus areas within the machine learning world, which is a separate topic altogether). This is particularly relevant for large industrial businesses striving to cut costs by preventing unplanned operational downtime. Unfortunately, the bulk of the effort in deploying machine learning solutions geared toward business value is that one of the most difficult aspects of this process is actually delivering and demonstrating value to customers.


In the world of machine learning, over 80% of the work revolves around cleaning and preparing data for analysis, which comes before the sexy machine learning part (see this recent Forbes article for some survey results supporting this claim). The remaining 20% involves tuning and validating results from a machine learning model(s). Unfortunately, this calculation fails to account for the most important element of the process; extracting value from the model output.

In business, the goal is to gain value from predictive model accuracy (another subjective topic area worthy of its own dialog). We have found that this is the most difficult aspect of deploying predictive analytics for industrial equipment. In my experience, the breakdown of effort required from beginning (data prep) to end (demonstrating business value) is really more like:

40% Cleaning/Preparing the Data

10% Creating/Validating a well performing machine learning model/s

50% Demonstrating Business Value by operationalizing the output of the model

The latter 50% is something that is rarely discussed in machine learning conversations (with the aforementioned exception). Veeramachaneni is right. It makes a lot of sense to keep models simple if you can, cast a wide net to explore more problems, don’t assume you need all of the data, and automate as much as you can. Predikto is doing all of these things. But again, this is only half the battle. Once you have each of the above elements tackled, you still have to:

Provide an outlet for near-real-time performance auditing. In our market (heavy industry), customers want proof that the models work with their historical data, with their “not so perfect” data today, and with their data in the future. The right solution provides fully transparent and consistent access to detailed auditing data from top to bottom; from what data are used to how models are developed, and how the output is being used. This is not only about trust, but it’s about a continuous improvement process.

Provide an interface for users to tune output to fit operational needs and appetites. Tuning output (not the model) is everything. Users want to set their own thresholds for each output, respectively, and have the option to return to a previous setting on the fly, should operating conditions change. One person’s red-alert is not the same as another’s, and this all may be different tomorrow.

Provide a means for taking action from the model output (i.e., the predictions). Users of our predictive output are fleet managers and maintenance technicians. Even with highly precise, high coverage machine learning models, the first thing they all ask is What do I do with this information? They need an easy-to-use, configurable interface that allows them to take a prediction notification, originating from a predicted probability, to business action in a single click. For us, it is often the creation of an inspection work order in an effort to prevent a predicted equipment failure.

Predikto has learned by doing, and iterating. We understand how to get value from machine learning output, and it’s been a big challenge. This understanding led us to create the Predikto Enterprise Platform®, Predikto MAX® [patent pending], and the Predikto Maintain® user interface. We scale across many potential use cases automatically (regardless of the type of equipment), we test countless model specifications on the fly, we give some control to the customer in terms of interfacing with the predictive output, and we provide an outlet for them to take action from their predictions and show value.

As to the missing 50% discussed above, we tackle it directly with Predikto Maintain® and we believe this is why our customers are seeing value from our software.


Robert Morris, Ph.D. is Co-founder and Chief Science/Technology Officer at Predikto, Inc. (and former Associate Professor at University of Texas at Dallas).

Predictive maintenance is not for me…


… because that’s not how it’s done in our market
Well, what shall I say? Prepare for the tsunami! While it’s true that switching (fully or partially) to predictive maintenance requires a transformation of how business is done, one thing is for sure: in every (!) market, there’s bound to be a player who moves first. And predictive maintenance has such disruptive potential that the first-mover advantage may be much larger than many executives suspect. The truth in the statement lies in the fact that many stakeholders, not in the least the mechanics, need to be taught how to deal with the prescriptions resulting from predictive analytics. And this – like most change processes – will require determination, drive and  a lot of training in order to make the transition successful. I believe it was Steve Jobs who once said something along the lines of ‘People don’t know they need something until I show it to them’. The same goes for predictive maintenance; it’s not whether the market (any market!) is moving that way, it’s about when and who will be leading the pack.
… because we don’t have data
Aaah, the ‘garbage in, garbage out’ argument. Obviously this is a true statement. But ‘we don’t have data’ typically points to different issues than what the statement says; most often it refers to either the fact ‘there is data but we don’t know where’ (as it’s often spread across many different systems – ERP, CRM, MRO, MMO, etc.), or it points to the fact that ‘we have no clue what you need’. Predictive analytics are associated with Big Data and, while often true that more data is better, this doesn’t have to be the case. I’ve seen many, surprisingly good, predictions from very limited data sets. So what’s key here? Work with partners who can easily ingest data from different sources, in different formats, etc. Also work with partners who can point you towards the data you need; you’d be surprised at how much of it you already have.
… because we don’t have sensors
A refinement on the previous objection and this one slightly more to the point. Many predictive maintenance applications  – but not all – require equipment status data. However, as we’ve seen from the first objection, a full roll-out of predictive maintenance approach may have to overcome organisational hurdles and take time. Therefore, start with the low-hanging fruit and gradually get a buy-in from the organisation through early successes. What’s more, upon inspection, we often find plenty of sensors, either unbeknownst to the client or in situations where the client doesn’t have access to the sensor data (in many cases, they do have access to the data but can’t interpret it – a case where automated data analytics can help!).
… because we don’t have a business case
This is worrying for a number of reasons; not the least because companies should at least have investigated what the potential impact could be to their business of new technologies, business concepts, etc. The lack of a business case make come from a lack of understanding of predictive maintenance and unlike as described in the last argument, a denial of this lack of understanding. As we know by now, one of the main (but not only) benefits of predictive maintenance is the moving of unplanned maintenance to planned maintenance. According to cross-industry consensus, unplanned maintenance is 3x-9x more expensive compared to planned maintenance. The impact of moving one to the other is obvious! However, many companies fail to track what’s planned and what’s unplanned and therefore have no idea on potential savings that could be generated by predictive analytics. Lacking this KPI, it also seems impossible to assess other impacts such as customer satisfaction, employee satisfaction, reliability improvements, etc.
… because our maintenance organisation is already stretched out
Let’s say we have a prediction for a failure and want to move it to planned maintenance (the event is still taking place but it’s nature changes). A commonly heard objection is ‘but my maintenance planning is already full’. Well, what would you do when the failure occurs? In that case, a maintenance event would still take place, only it would either upset the maintenance planning or would be executed by a specific ‘unplanned maintenance’ intervention team. Either way, time and money can be saved by predicting the event and executing the maintenance during a planned downtime. As a matter of fact, moving unplanned to planned actually frees up maintenance time and resources (to be totally correct: after an initial workload increase to catch up to the zero point). The opposite is actually called ‘the vicious circle of maintenance’: unplanned events disrupt maintenance planning, which is therefore often not fully or perfectly executed, which in turn generates more unplanned events, etc.
… because we don’t trust the predictions
Humans are not wired for statistics! While we have a natural propensity for pattern recognition, this talent also tends to fool us into wrong conclusions… Any predictive maintenance (or, by extension, any predictive analytics project) initiative should be accompanied by good training to make sure predictions are interpreted correctly. Even better, business apps tuned towards individual job requirements which translate the prediction into circumstantial actions should be developed and deployed. At the current state of affairs, starting with a limited scope project (call it a pilot or POC), should allow the delivery team to validate the presence of enough and good enough data, build the business case, etc.
… because we don’t understand predictive maintenance
Well, at least they’re being honest! Companies that are aware of their lack of understanding are halfway down the path towards the cure…
Understanding predictive maintenance starts with understanding predictions (see above) but then also seeing how this affects your business; operationally, financially, commercially, etc. Predictive, and by extension prescriptive, maintenance has  far-reaching impact, both internal and external (non-predictive approaches will have a hard time competing with well-implemented predictive maintenance organisations!).
These are, by far, not all the objections we encounter but they give a general idea of how/why many organisations are scared of the currently ongoing change. As with so many technological or business advances, it’s often easier to formulate objections that to stick one’s neck out and back up the new approach. However, as history has shown us (in general and with regards to maintenance as shown by the evolution from reactive > proactive > condition based), maintenance is inevitably evolving this way. Getting it right is hard but not getting it is expensive! We’ll inevitably get front-runners and a flock of successful followers but many of the late starters will simply be run over by more efficient and effective competitors. Business is changing at an ever-faster pace and executives have to be ever-more flexible at adapting to the changing environment. Make sure you get one or more trustworthy partners to introduce you to the concepts and tools for predictive maintenance. At this time of writing, the front-runners are already out of the starting blocks!