“Automation” is the way forward into traditional application maintenance and support (AMS) and take it to a new level of support. With one critical decision to automate AMS, businesses can minimize or eliminate teasing tech problems and stay focused in their business. Importantly, the decision delivers cost reduction, it consolidates fragmented operations, eliminates process gaps, and maximize productivity. Even better, the decision comes with a bonus: By focusing on automation, businesses can continue with their existing applications and processes without sacrificing user experience.

Automated AMS (AAMS) is an 91¶¶Ňő solution based on decades of AMS experience in the F&B, retail, manufacturing, BFSI and the travel and hospitality industries. AAMS is a quantifiable and customizable approach that comes with guaranteed increase in Net Promoter Scope (NPS), resource(s) optimization and cost reduction based on client base. Much to the relief of CTOs, AAMS also has the power to eliminate the dependence on vendors, unleashing flexibility.

91¶¶Ňő’s AAMS offering is focused on improving three key vectors: Customer Experience (via an emphasis on self-service), Operations Optimization (to impact efficiency) and business value services (increased effectiveness) with strong experience SLA’s (XSLA’s) which are beyond regular SLA’s. Experience SLA’s can only be offered by providers with strong domain expertise, efficient service model and automation complimenting each other.

Using highly sophisticated domain-centric playbooks, knowledge repositories, accelerators, application optimization techniques, and self-healing bots. The solution deploys customizable Integrated Design and Development Platform (IDDP), a feature of the AAMS offering, that eases the application build and release process as self-service function.

With IDDP, clients can release applications with over >95% confidence and replace their weekend release schedules with any-time-of-week three-hour release plans. Clients can also leverage a large portfolio of assets and solutions around application optimization, co-Innovation, cloud native applications, and more.

The AAMS portfolio offers customized services around:

• Accelerated Transformation
  • SAFe agile AMS transition
  • Co-innovation charter
  • Cloud native application transformation
  • Application optimization
• Operational Efficiencies
  • Automation led shift-left approach
  • AI-based resolutions and recommendations
  • User persona-based BOT assistance
  • Transparency through business metrics dashboard
• Customer Experience
  • Self-service and self-healing
  • Process and knowledge assistants
• Business Resilience
  • Business metrics-led support services
  • Tool based application assessments and insights
  • Incidence avoidance through monitoring and AI

A feature of the AAMS that our clients like—aside from the IDDP, Chatbots, and more—is the Customer Value Realization. This is a dashboard that extracts learnings from monitoring the existing applications. It helps answer questions like, “Who uses application & which function? When is it used? what is the value realized?” This analysis allows clients to determine and introduce new features while retiring those that have outlived their relevance.

However, the feature that tilts clients into choosing our expertise is that the automation provides an accelerated start, allowing us to acquire and shape data from legacy systems (such as those that may be in use for supply chain functions) and pump them into modern downstream mobile applications, portals or other digital platforms.

Bundled with features that make AMS simple and cost-effective, AAMS is the logical future for businesses that need to constantly improve their applications across sites, generating value for managements for the investments made in maintaining applications.

Co-authored by:

Ashok MVN
Technology Partner – ADM
91¶¶Ňő

Divyadarshan Jannu
Solutions Lead
91¶¶Ňő

The post Taking AMS to the new level with automation appeared first on 91¶¶Ňő.

Airlines have multiple brands and a host of alliance partners that make planning complex. A small change can have a large impact on flight schedules, fuel costs, workforce availability, passenger safety, etc. Practically every function—from Human Resource to Finance, Sales & Distribution, Commercial & Planning, and Maintenance, Repair and Operations—is affected by change. But airlines are unable to control and mitigate the impact this has on customer experience and bottom lines. This is because each function is siloed and spreadsheets continue to be the most popular way to manage processes. The result is slow, error prone decision-making. This puts accurate financial and operational planning beyond the grasp of most airlines.Ěý

Progressive airlines are using connected planning to drive accurate & precise financial & operational planning.

A connected planning platform ensures that teams across functions can collaborate in real time. These platforms help them get away from their spreadsheets that are incapable of drawing insights from the billions of data points that airlines generate. Instead, the connected platform uses analytics and forecasting models to drive accurate and precise financial and operational planning in real time. 91¶¶Ňő, leverages its partnership with Anaplan, a leader in the connected planning space, to deliver cloud-based pre-built airline-specific solutions that improve visibility into operations, boost productivity and lower costs.

There are airlines like AirAsia Expedia that have greatly benefited from an Anaplan-based solution. The FP&A head of Expedia says they are now doing scenario planning and sensitivity analysis for the whole business across Asia and dynamically understand where the business is and where it’s going.

Effective planning by connecting applications and functions across the business using connected planning

Our experience shows that airlines recognize the urgent need for connected planning but are hesitant to adopt the solution. They feel they are already using other, more traditional systems that have been around for ages, which can eventually be leveraged to improve financial and operational planning. This is understandable, especially as the industry is cash strapped and going through an extremely challenging phase. There can be no doubt that traditional systems have served their purpose. But today, they impede speed and agility because of their siloed nature. Anaplan is the only platform that can bring about effective planning by connecting applications and functions across the business.Ěý

91¶¶Ňő is a Strategic Partner for Our Clients on Connected PlanningĚý

91¶¶Ňő with its domain expertise in airlines, CPG and manufacturing and its strategic partnership with Anaplan has built a Center of Excellence focused on Intelligent Planning and Execution with 50+ certified Anaplan consultants, 10+ solution architects & master Anaplanners, 60+ deployments across 22+ use cases. We offer services from strategy, implementation and managed services for the planning solutions and also help customers setup & scale their own Planning CoEs.Ěý

Our 3*3*3 Approach to Jumpstart the Program and Scale With Additional Use Cases

91¶¶Ňő can use its expertise to identify potential use cases aligned to your airline’s business objectives and set up 3 day, 3-week and 3-month pilot programs. The pilots will demonstrate proof of value and define a future roadmap. In the next 3 to 9 months the implementation can be scaled based on use cases and target ROI.Ěý

Our experience in creating Financial and Operational planning solutions across diverse industries has shown that starting cautiously works. It leads to a better understanding and appreciation of the potential that connected planning holds. If you want on-the-fly adaptability, improved decision-making, and accurate scenario planning to guide your airline business, a connected planning solution is an essential ingredient of success. For more information please read our Connected Planning Turbocharge the Airline Growth Powered by Anaplan

Author:

Amit Paul
GM, Intelligent Planning and Execution
91¶¶Ňő

Peeyush Goel
Industry Consulting Head – Travel
91¶¶Ňő

The post Airlines With Accurate On-The-Fly Financial and Operational Planning Are Taking Off for Growth appeared first on 91¶¶Ňő.

The post Fly High, Adopt Personalized Managed Services appeared first on 91¶¶Ňő.

Adopt ML-based optimal booking strategy to maximize the yield and revenues

Overbooking flights is a common practice in the aviation industry based on the expectation that some fraction of the booked passengers will either cancel their booking at the eleventh hour or fail to show up at the departure gate (commonly known as no-show). Accurate forecasts of the number of no-show passengers for each flight can help the airline to accrue more revenue by simultaneously reducing the number of spoiled seats and lowering the cases of involuntary denied boarding which produce significant cost penalty. Optimal booking policies seek to maximize the yield as a tradeoff between the revenue due to additional sales offset by the cost of any denied boarding that might happen. Flights flying fully occupied are not only of economic interest but are of ecological importance as well.

Implementation of relevant statistical/machine learning based algorithms may ensure an advanced and robust prediction of the no-show numbers for each scheduled flight, which can aid the airlines company to accept optimum number of additional bookings over the inventory capacity. The solution comprised of two steps – prediction of cabin-level no show rates using specific information on the individual passengers booked on each flight and later employing these predicted no-show rates along with features extracted from historically similar flights to arrive at the final no-show estimate.

Build a robust prediction framework to identify no-shows

At the beginning, individual passenger details from historical flights were utilized to capture their booking trend and understand their travel pattern. Different classification models were employed to capture the different bias-variance structures and then ensembled together to come up with a more robust prediction framework. Identification of individual learners that will eventually lead to lower misclassification is the key. Below is the mis classification table.

Here B2 are the cases where a passenger predicted as flown have actually flown. A1 are the cases where one predicted as no-show didn’t turn up. The passengers who have been predicted to be flown passenger but in reality didn’t turn up are A2. B1 are the passengers who have been predicted to not turn up but eventually did. Though both A2 and B1 cases are misclassified, an increased number of B1 cases will result into higher instances of denied boarding which will escalate the cost in the form of penalty.

At the next step some generalized linear model concepts were employed to come up with the estimated no show numbers. A GLM model for the unique combination of i^th Flight Market Departure Date is of the form:

g(y_i) = f(x_i) + ε_i

where g() is the appropriate link function applied on the response variable, that would help to model it as a linear function of the explanatory variables. In this case, f() is a linear function and ε is the corresponding error vector.

While experts will agree that individual passenger information for a particular flight is of immense importance, airlines usually accept bookings till few hours before departure, and hence any model based on the same data will be too volatile, and always be based out of incomplete data. Rather, we assume that the pattern of travelers in a particular Flight- Market would be similar in certain Days of Week. So, we utilize the cabin level no show rate from the first model as an auxiliary variable for the passenger level information in a GLM (Generalized Linear Model).Ěý We used GLM over other because of following reasons

• The response variable is a count variable (more than 0 but less than a certain number, which may vary from Market to Market)
• The variance structure of the error will guide on the selection of the appropriate link function
• The response variable might also be taken to be of type ratio (rate of no show) and may guide to selection of a totally different link function

A GLM yielding lower RMSE (Root Mean Square Error) values is considered as an appropriate prediction equation.

The General workflow can be summarized by the below diagram:

Improved inventory visibility and intelligent network planning for airlines

Some benefits reaped by the Airlines those have implemented Optimal Overbooking Strategy are:

• Reduction of spoiled seats as well as the number of involuntarily denied boarding that not only maximized the revenue of the airlines due to additional bookings but also curtailed additional cost due to compensation due to DNBs and gave a boost to the reputation of the company
• Accurate prediction teamed with historical booking pattern helped the client in network planning and inventory management

How scenario changes post pandemic

COVID-19 has changed how industries operate and Aviation is no exception. Most of the airlines worldwide had been grounded and very few are operating across limited routes. Some Indian airlines have started their domestic and international operations, but the number of flights deployed is just a fraction of their pre-pandemic frequency. Center for Aviation (CAPA) India has indeed stated that, “Indian Aviation Sector may lose $4 billion in FY 21.”* Currently, with limited transportation options, airlines is the only viable mode of transportation as people stranded in places away from home has an urge to return to near and dear ones.

In such trying situations having an Optimal Booking Policy at place can truly help sustain airlines. Though prediction of overbooking becomes more difficult in such an unprecedented situation, the airlines deems it to be even more important to have a robust and accurate demand forecast along with an Overbooking Strategy. Smart deployment of inventory along with the decision to set the Optimum Booking Limit, might help in the yield management more than ever.

New consideration of factors like instances of relaxation or implementation of sudden lockdown due to increasing cases of Corona outbreak at respective cities are important as this may result into cancellation of tickets for some passengers due to lack of transportation facilities giving room for overbooking.

Though one might say that the future of aviation looks bleak in current scenario, with the right changes applied at the right time to the existing model, we have the potential to maximize the revenue of an airline today and in the future.

We are building capabilities like these using AI/ML for optimal overbooking strategy in our platform of intelligence for airlines. Our platform can help airlines accelerate the value realization – 2% incremental PLF, 4% savings in fuel 3% upside in crew utilization and 2% improvement in TAT – using airline intelligence platform.

Stay tuned to know more about for .

Authors:

Devangana Dasgupta
Data Scientist, DATA

Akshay Vijay Medhane
Junior Data Scientist, DATA

Anindya Neogi
GM, Chief Data Scientist, Digital Experience

References

• “Passenger Based Predictive Modelling of Airline No Show Rates” – Richard D. Lawrence, Se June Hong, Jacques Cherrier
• “Forecasting and Forecast Combination in Airline Revenue Management Applications” – Christian Lemke, Bogdan Gabrys
• “Cancellation Predictor for Revenue Management applied in the Hospitality Industry” – R. van Leeuwen
• Categorical Data Analysis, Second Edition – Andre Agresti

The post Optimal Overbooking Strategy of Airlines using Statistical/Machine Learning Algorithms & their use in post pandemic situation – an expert view appeared first on 91¶¶Ňő.

Source : ICAO estimates ()

Figure1: Estimated impact on international passenger traffic and revenue by region for 2020

There are two broad categories where we see a major impact:

1. Direct and immediate:ĚýThe drastic reduction in demand has eliminated incoming revenues. Booking cancellations and running opex have forced most global airlines to ground the entire commercial passenger fleet and some have filed for bankruptcy. Air Mauritius and Virgin Australia are just two such examples.⁵ĚýTypically, even with a grounded fleet, airlines have to still bear 40% of operational costs in MRO activities. Aircraft have not been designed to be grounded for such long durations—a 70 to 90 ton structure standing still in a hanger or on the tarmac for weeks on end undergoes structural stress. The maintenance and assurance it would take to make these aircraft air worthy again for an average fleet size of 100+ would be staggering.
2. Cascaded long term:ĚýTravel is an essential part of life and business. While virtual communication is a necessity at the moment, humans cannot keep their desire to travel, and for personal interactions, in check for long. The question is, how comfortable are we going to be sitting a few inches away from an unknown person in a closed air-locked aircraft for long hours?

The single ray of hope lies in the fact that many global efforts to test a vaccine against the coronavirus are in fast forward mode. As of 23 April, there were six vaccines in clinical evaluation, and 77 in pre-clinical evaluation.⁶ĚýBill Gates who is taking a major interest in vaccine development (the Bill and Melinda Gates Foundation has a COVID-19 therapeutics accelerator⁷) says that one could be in commercial production in the next 18 months.⁸

The aviation industry cannot afford to wait and watch the situation. It must be pro-active. This is the crisis when leaders, despite the odds, can reset and re-shape the future. Our analysis suggests there should be two sets of parallel teams who should be addressing the crisis:

• Team 1 should be working relentlessly to reduce costs and cut losses
• Team 2 should be working on a plan for revival the moment the COVID-19 curve is flattened or a vaccine becomes commercially available

Expecting a 100% normal world in the next few months is absurd. But there appear to be signs that recovery can be quicker than expected, at least in pockets around the world. Bloomberg Economics recently estimated that 85% of activity had returned to China, excluding Hubei province.⁹ĚýChina is also putting in place processes that enable workers to return to factories and offices. These processes are shaping new habits and social dynamics (some very interesting insights to be gained here).¹⁰ĚýIf they work, these processes may be replicated in other parts of the world. This will be the new normal and will take us months and even years to get accustomed to.

Meanwhile, some things that have drawn our attention when exchanging views with friends in the industry or reading aviation-related research:

• Airlines are investing in customer communication related to new destinations and the new processes they are putting in place to engage customers and retain them in a post-COVID-19 world. Some ideas distilled from our interactions with the airline and hospitality industry include:
  • Create and publicize new no-touch processes, especially in areas such as automated baggage handling, biometric based check ins, remote processes for employees to minimize physical presence and interaction
  • Work with airports to create touchless, biometrics-based boarding gates manned by robots
  • Showcase new mobile and interaction tools such as voice-based in-room assistants used to service customers
  • Create examples around usage of robots and automation for guest/ customer safety and comfort (for example, in-flight videos on how cabins are sanitized, adherence to hygiene standards in the preparation and handling of in-flight meals, etc.)
  • Provide engagement opportunities to guests/ customers by webcasting cocktail and cooking classes, yoga that can be practices mid-flight for healthier air travel, etc.
  • Leverage VR to send guests on “holidays” to hotel properties or airline destinations
• Determine the optimal size and dimension of networks and fleet within the next few weeks
• ConsiderĚýM&A and consolidation opportunities; we hear many businesses are considering joining hands while operating certain sectors or market geographies
• Make a stringent checklist for sanitization and hygiene factors and an aircraft certification process for every flight operation to win back customer confidence
• Design new business processes and invest in smart technologies, including IOT, for a contactless flying experience
• Re-look at financial settlements with partnering channels and participating vendors to cut credit time – and better still, to make all settlements almost real-time

Over the last decade, many airlines have become a set of smaller organizations, with regional operations, low cost brands, specialized cargo businesses, etc. It is time to centralize the data across these organizations and use real-time analytics to create synergies, cost saving opportunities and improved efficiencies.

We created a Data centric framework aiming on 4 strategic objective themes:

Ěý Ěý Ěý Ěý Ěý Ěý ĚýĚýĚý Ěý Ěý Ěý Ěý Ěý Ěý Ěý

Each strategic theme will aim to achieve business outcomes that will help airlines realize both its short- and long-term goals in becoming a true digitally transformed airline.

Many of our industry friends are utilizing this time to conceptualize a Lean-IT organization, including offshoring much of their application portfolio and to strengthen their contact centre experience by leveraging cloud, while many are considering ways to use automation to improve operational processes and reduce costs. Finally, some airlines are using sophisticated analytics to back their demand stimulation programs—packages, discounts, loyalty programs, etc., that can be applied to sectors that begin to show lift. And the lift will come, because if anything is inventive and resilient, it is us humans.

Author:
Peeyush Goel
Associate Partner (Consulting Services – Travel & Hospitality)

Reference:

1. EU Travel Ban: Air France and France Most Vulnerable

The post Flying beyond COVID-19 appeared first on 91¶¶Ňő.

Let’s examine the ancillary revenue of Spirit Airlines, a leading ULCC (Ultra Low Cost Carriers) (see Figure 1). Its ancillary revenue is 47% of total operating revenue.Ěý If we classify ancillary revenue into two categories –need-based and experience-based—it is evident that most ancillary revenue for Spirit is from need-based ancillaries such as baggage and assigned seats.

ĚýĚý Ěý Ěý Ěý Ěý Ěý Ěý Ěý

ĚýĚý Ěý Ěý Ěý Ěý Ěý Ěý Ěý Ěý Ěý Ěý Ěý Ěý Figure 1: Spirit Airlines²

This leaves a large opportunity in experience-based ancillary offerings, especially for LCC (Low Cost Carriers) and ULCC, where most services are un-bundled. However the trend, even in FSC (Full Service Carrier), is to move towards becoming a LCC. This is evident from the fact that several global FSC are now charging for seat allocations.

With the availability of customer data and the evolution of analytical technologies and models, we believe that experience-based ancillary can add substantially to bottom lines in the travel and hospitality industry.

It is practically impossible for an airline or a hotel to influence demand for need-based ancillaries. However businesses can use a variety of levers to boost demand for experiences (which can also help improve the loyalty base of a business).

Experience-based revenue would come from an in-depth understanding of the customer. There are many initiatives being taken to create a 360 degree view of the customer to boost sales. But the problem is that the 360 degree view alone may no longer be adequate in today’s dynamic digital era.

A 360 degree view is a starting point. True maturity is when we build a 720 degree view of the customer’s genome. In today’s competitive but interconnected world it is necessary to understand the customer from more than one perspective. Figure 2 shows the various sources of customer data that the travel and hospitality industry could access and the data sciences that can extract customer insights that can lead to experience-based ancillary service.

When we apply Deep Data Science on the various data available to create a customer genome, we gain visibility into the customer’s Context, Preference, Propensity, Affinity, Behavior and Personality. Using this information, businesses need to draw a matrix of Journey Phase and Activities as shown in Figure 3. The matrix exposes opportunities across three primary areas: Customer Delight, Cross Sell-Up Sell and Service Recovery. Each is a key ingredient of successful experience-based ancillary services.
Figure 2: Illustration of Various available data and the data sciences to be applied

ĚýĚý Ěý Ěý Ěý Ěý Figure 3: A sample matrix between Journey Phase and Activities

Some illustrative examples help understand how this matrix operates. Assume that a customer is fractionally short of a loyalty category upgrade (for example, from Silver to Gold). It is possible to identify this and use the information when the customer requests an early check-in or a late-check out and offer the service free (see Figure 4 for examples of leveraging customer data to improve experience-based ancillary revenue). Or the hotel could provide meeting lounge access or a weekend tour package to such a business customer at a discount.

There is a sound reason to build experience-based ancillary revenue. In a volatile industry like travel and hospitality, fares and room tariffs are subject to change based on competitive pressure, demand, regulatory directives, etc. Increasing the revenue streams from ancillaries that are not affected by these pressures, results in more stable and predictable revenue.

Experience-based ancillaries are also critical in increasing the loyalty base. Consider the example of a hotel guest (see Figure 4) and how business can use data, analytics platforms and business rules to offer Customer Delight, Cross Sell-Up Sell and Service Recovery.

Figure 4: Using data to grow experience-based ancillary revenue and boost loyalty

The Customer Experience Management (CEM) platform, which forms the middle layer, analyses the customer needs in context and maps it to historical data in real time and generates/offers the right experience to the guest. In this example the hotel has not only generated ancillary revenue but has also provided experiences that help elevate the customer higher in the loyalty value chain.

Need-based ancillary revenue will, inevitably, begin to plateau as supply of most ancillary services is finite. However, experience-based services can continue to expand and grow, depending on the ingenuity of the business.

The post Exploring revenue generation from a new ancillary category in travel and hospitality appeared first on 91¶¶Ňő.

Businesses that have used technology to intelligently personalize and customize the travel experience are winning. They are creating sharply personalized product bundles. These have the power to draw the attention of more customers, drive loyalty and earn free marketing mileage when their customers amplify their brands through social media.

Digital changes everything

The real change has been in the limitations enforced by digital: Opportunities for in-person interactions have become limited, curbing the ability to influence customers. Simultaneously the 24X7 online service options available to customers has increased manifold (as an example, more than ) and social media has become an important component in the customer’s decision-making process.

The bottom line is that to acquire customers and retain them requires a massive effort. Advanced technology, ranging from predictive analytics to Big Data, Machine Learning, Artificial Intelligence (AI), Robotic Process Automation (RPA), Augmented Reality (AR)/ Virtual Reality (VR) and Natural Language Processing (NLP), needs to be brought into play to keep customers engaged with information, offers, and experiences. Failing to do so will only increase the gap between booked and realized revenue.

The quality of CX can tilt the game for your business. In one study, the Temkin Group found that companies that earn $1 billion in annual revenue can expect to earn, on average, an additional $700 million within 3 years of investing in CX¹.There is one more noteworthy change taking place in customer behavior. Traditionally, businesses in the Travel & Hospitality industry depended on customer complaints and feedback to make improvements and deliver new services; today, studies have shown that 96% of customers don’t bother to complain and 91% don’t come back². And just how important is social media? One study showed that 52% of travelers were so influenced by social media they changed their original travel plans and 87% of those younger than 34 are using social media to solicit advice before making bookings.³

The power of channel integration

The vectors that influence and guide customers has changed dramatically. The experience for most customers begins even before they arrive at an airport, a hotel, business conference or an attraction. It begins with the ease of acquiring information, comparing prices, booking air and surface transport, confirmations, making special requests, completing insurance and the scores of other details that go into stress-free travel.

Typically, a customer today interacts with multiple channels (see Figure 1) to complete travel plans, negotiate the price and share and sync information with all parties if a disruption occurs.

Figure 1

The customer doesn’t want to interact with different entities for each requirement and provide the same personal and travel details repeatedly (and sometimes make mistakes in data entry!). Businesses that aim to present the customer with a one-stop shop for all travel requirements could easily become the preferred destination for travel needs. Services from different channel partners can be integrated and presented in a customized and personalized manner based on customer data. The customer uses a single interface to complete all bookings without being exposed to the channel partners (see Figure 2).

Figure 2

Take one more step into the future

But far sighted businesses in the Travel & Hospitality industry are going one step further. They are examining the possibility of creating digital twins that can aid customers in viewing and completing the entire journey in one seamless phase. Until now, most initiatives have been around the Plan & Book phase. Once this phase is done, the customer is ignored. Going beyond this ensures product differentiation.

With the availability of data, it has become possible to create context aware personalization across every step of the journey (see Figure 3). We call this CX 4.0. It resonates with the customer’s “moment of truth”. It distinguishes itself by creating first-time-right, intelligent, targeted, and value-based CX.

Figure 3

Today’s Travel & Hospitality businesses cannot afford to think of offering anything less than CX 4.0. With the explosion of technology, CX 4.0 is within grasp. Is your business ready to reach out for it?

The post CX 4.0: A journey into personalization and customization appeared first on 91¶¶Ňő.

Designing an analytical approach to optimize “tankered fuel” with minimal impact on fuel burn rate to reduce operations cost.

The Challenge Faced by the Airline Industry

In our previous blog, it was established that fuel costs contribute, on an average, 25%-30% of airline operations costs. In this regard, one of the key focus areas is fuel procurement. At the fuel procurement stage, airlines have at least two industry practices to focus upon:

1. Secure fuel supply at minimum price possible by hedging (a medium/long-term activity)
2. Procure maximum fuel possible at the lowest price possible by tankering (a tactical activity)

Conventional fuel tankering is purely based on fuel-price differential across airports. However, a more comprehensive approach is needed since fuel tankering is dependent upon multiple factors such as fuel burn, aircraft specification, weight distribution, flight path traversed, and weather information (for instance, wind speed and direction), etc. Such diverse factors make estimation of fuel tankering, on a near-real time basis, a challenging task, one that hinges upon integration of data from diverse source applications – both internal & external.

In the current context, the primary objective is to estimate optimal quality of fuel, intertwined to procurement cost, basis the (optimal) utilization of fuel across different costs, to optimize overall network cost, leading to minimal wastage, if any.

Understanding the Current Industry Landscape

Let us first understand the industry landscape in terms of fuel tankering as a phenomenon, by glancing through a few numbers. In the ECAC (European Civil Aviation Conference) area, full tankering could be performed on 16.5% of flights (on per-year basis), whereas partial tankering could be performed on 4.5% of flights. In more than 10 million flights annually in ECAC, the estimation is that 2.1 million perform fuel tankering. The breakup is as follows: 1.6 million flights (16.5%) perform full tankering and 0.45 million (4.5%) perform partial tankering. In practice, full tankering is performed on 15% of flights.

Fuel tankering would represent 136 KG of additional fuel burnt per flight concerned (costing €75), generating 428 KG of additional CO₂ (i.e. 9€ in purchased CO₂ allowances). In spite of the added cost, on average, fuel tankering can result in a net saving of €126 per flight. Having said that, it is extremely important that fuel supply is optimized through efficient tankering strategy, while ensuring optimal emission so that environmental policies are not violated.Ěý

How Technology can Lead the Way

With advancement in technology, a fuel tankering system or application may get integrated into flight planning system, such as 91¶¶Ňő’s Flight Planner, which would help fuel tankering decision on a real-time situation, based on multiple parameters. It will have capabilities to simulate hundreds of scenarios based on flight path, fuel usage, weather conditions, weight and balance, etc. Hence, the tankering solution must be designed using a scalable algorithm, which can generate insights on a real-time basis, and contribute to an optimal flight plan construct.

The Solution

Since there are fuel price variations across stations, airlines tanker more fuel from departure station to minimize supply cost. However, additional fuel results in additional weight leading to high burn rate. Keeping in mind aircraft specifications and airport rules, a non-linear optimization framework has been designed with following dimensions being included in the solution.

• Maximum takeoff weight/maximum landing weight
• Fuel capacity of the aircraft
• Regulatory norms of fuel uptake in different airport stations
• Fuel benchmark based on historical flight patterns
• Engine operating efficiency

The objective is to minimize total fuel supply cost across different stations for all the aircraft flying in different rotations. Essentially, that narrows down our entire approach to the following inequality:

Let us introduce a few mathematical notations at this point to formulate the problem into a solvable equation.

At time point t=1,

At time point t=2,

Using mathematical induction, we can derive that

So total fuel left can be calculated as:

Replacing equation (5) in equation (1), we achieve the objective function of our optimization solution suite. Coming to operational constraints for the current optimization, here are the key boundary conditions in the process of designing the optimal solution.

Different sets of data that are considered while designing the solutions are as follows:

• Block-hour information for the entire network
• Maximum takeoff weight and maximum landing weight
• Maximum fuel capacity of the aircraft
• Passenger demand forecast
• Cargo load and estimated weight
• Weather information
• Fuel consumption planning information
• Airport policies in terms of fuel reserve and fuel uptake

We designed the problem into a multi-objective optimization framework where the objectives are to minimize supply fuel cost, and at the same time, minimize leftover fuel at the end of each rotation. We used differential evolution algorithm to solve the optimization problem. Tuning of individual parameters in DE was trained using Genetic Algorithm/Simulated Annealing. For individual passenger demand forecast framework, an ensemble approach combining regularized regression and Extreme Gradient Boosting (XGB) followed by a stacked RNN (GRU) was used.

Business Benefits

In our assessment and experience, predictive-analytics-based optimization approach in tankering could lead to 2.5%-2.7% potential cost savings. This is above the industry benchmark of 1%-1.5%.

A what-if simulator, designed and integrated with the tankering optimization solution, helps the business user, in this case Flight Ops team, to simulate scenarios and adopt the best tankering strategy – one based on not just fuel price fluctuations, but also changes in other key parameters.

The post Efficient way to tanker fuel using a mathematical optimization model appeared first on 91¶¶Ňő.

Price, attention, delivery speed, quality, service – the parameters for brands to compete are many and to say it’s a battle out there to gain customer loyalty is an understatement; it’s pure savagery! Customers today openly scrutinize and share unforgiving opinions influencing a huge number of people, thanks to social media channels that have given a voice to the masses. No organization can now afford to ignore customer demands. Understanding them is therefore important and data takes the front seat in this scenario. Let’s look at the various options and approaches before brands to leverage data to their advantage.

Loyalty and Customer Data Platform (CDP)

There are no linear paths to purchases anymore. Customers take the curvy path of research before zeroing in on a purchase and this includes e-commerce websites and apps, physical stores, web forms, search engines, social media and so on. Brands need to keep up with this zigzagging of customers and that’s what customer data platforms facilitate ¹. They gather relevant data and present it as a unified view, highly useful in hyper-personalization.

Data Science and Loyalty

While CDPs brings a wealth of data before brands, what to do with it is a question that data science answers. The power of data lies in being able to successfully use it to understand customer behavior at every step of the marketing funnel – from product awareness to activation. Data science brings forth quantifiable metrics that allow marketers to understand at which point a customer becomes disinterested in a product and drops off. It helps bring about personalization at this very point to enable sales conversion. Of course, when personalization is successful, loyalty naturally follows.

Understanding Customers Better through AI-Based Engagement Analysis

While data science brings customers the most effective stages to intervene, artificial intelligence aids in customizing and personalizing that engagement to bring about the desired results. Here’s how they help:

• Making highly relevant purchase recommendations
• Offering insights to make digital marketing efforts effective
• Predicting the likelihood of lead conversion
• Providing direction to sales agents
• Optimizing the lifetime value of customers through predictive analytics

Personalization through Machine Learning Models

According to McKinsey Digital, organizations that successfully personalize customer experiences enjoy the optimization of marketing spends by up to 30% ².ĚýAchieving this manually, however, is impossible and automation without intelligence can lead to ineffective personalization. Enter machine learning (ML) and the problem ceases to exist. ML algorithms allow for automatic identification of data (behavioral) patterns and suggest the best course of action without an explicit programming need for each scenario. The right mix of data and ML can help marketers build the perfect model for personalization.

Contextualization of Customer Journey

Customer lifecycle has different stages, and at each stage, the expectation is different. Moreover, the expectation differs with the nature of the business and its standing in the market. In order to be effective, the journey must be contextualized to the buyers’ preferences. It takes a dynamic combination of technologies discussed above and a practitioners’ understanding of the industry to achieve true personalization. Getting it right is only possible when you have a partner who adopts a consultative approach to offer your business a technology-led solution.

The post Loyalty in the Age of Hyper-Personalization appeared first on 91¶¶Ňő.