{"id":1407,"date":"2024-11-13T15:22:09","date_gmt":"2024-11-13T15:22:09","guid":{"rendered":"https:\/\/crp.trb.org\/acrpwebresource18\/primer\/"},"modified":"2024-11-13T21:16:42","modified_gmt":"2024-11-13T21:16:42","slug":"primer","status":"publish","type":"page","link":"https:\/\/crp.trb.org\/acrpwebresource18\/primer\/","title":{"rendered":"Primer"},"content":{"rendered":"
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Data Analytics Primer<\/h1>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Data analytics<\/a> encompasses a broad range of techniques and tools for examining data <\/span>to<\/span> discover insights, make predictions, and recommend actions<\/span> based on <\/span>the <\/span>findings <\/span>of<\/span> analytical models<\/span>. <\/span>Th<\/span>e<\/span> p<\/span>urpose of this p<\/span>rimer <\/span>is to <\/span>inform airports and key partners <\/span>of<\/span> the <\/span>best practices for effectively<\/span> implementing data analytics<\/a> to enhance<\/span> airport<\/span> operations<\/span> and improve the passenger expe<\/span>r<\/span>ience<\/span>. <\/span>It <\/span>provides<\/span> a basic overview of the methods and techniques used in data analytics<\/a>, describes the benefits and challenges of applying data analytics<\/a> in practice, and provides the steps for implementing data analytics<\/a>.<\/span> The primer<\/span> is intended for <\/span>airport <\/span>professionals<\/span> of all levels who are interested in implementing or improving their data analytics<\/a> practices.<\/span><\/span> <\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t

\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\"\"\t\t\t\t\t\t\t\t\t\t\t
Image credit: Everything Possible\/Shutterstock.com<\/figcaption>\n\t\t\t\t\t\t\t\t\t\t<\/figure>\n\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\n\t\t\t\t\t\t<\/span>\n\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Organization of the Primer<\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t

Select a section below to expand the information.<\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t

\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tData Analytics Overview <\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t

Data <\/span>analytics<\/a> approaches<\/span> are described in terms of their descriptive, predictive, and prescriptive functions and<\/span> are implemented using a <\/span>range<\/span> of procedures and techniques <\/span>that vary in complexity<\/span> to analyze<\/span> an array<\/span> of <\/span>different sources<\/span> of<\/span> information<\/span>. <\/span><\/span> <\/span> <\/span><\/p>

Descriptive analytics<\/a><\/span><\/b> is a proces<\/span>s <\/span>of<\/span> integrating and summarizing <\/span>data from multiple sources <\/span>and<\/span> communica<\/span>ting<\/span> information<\/span> about the data<\/span> via reporting dashboards<\/a><\/span> and data visualizations<\/span>.<\/span><\/span> <\/span><\/p>

Predictive analytics<\/a><\/span><\/b> involves<\/span> developing <\/span>advanced statistical <\/span>or computational <\/span>models to predict target <\/span>outcome<\/span>s<\/span> or <\/span>metrics.<\/span> P<\/span>redictive <\/span>models<\/span> for forecasting<\/a> can <\/span>vary in complexity, <\/span>includ<\/span>ing methods such<\/span> as<\/span> decision trees<\/span>, <\/span>linear regression<\/span>,<\/span> machine learning, <\/span>and artificial intelligence (AI)<\/a> algorithms.<\/span><\/span><\/p>

Prescriptive analytics<\/a><\/span><\/b> supports decision-making<\/span> by<\/span> recommend<\/span>ing a<\/span> course<\/span> o<\/span>f<\/span> action <\/span>to meet <\/span>business <\/span>objectives<\/span> based on<\/span> insights <\/span>gained<\/span> from descriptive <\/span>analysis <\/span>and predictive <\/span>models<\/span>.<\/span><\/span> <\/span><\/p>

There is no “one-size-fits-all” data analytics<\/a> solution for all use cases. Airports may implement data analytics<\/a> methods and techniques to address a variety of common business problems, such as traffic congestion, tracking passenger load at the airport, increased wait times at security, and issues related to overall customer service.<\/p>

Valuable insights can be gained from various types of data, including text, images, video, audio, and data from sensor devices that are analyzed using different analytics<\/a> methods. Text analytics<\/a> involves the analysis of textual information using standard natural language processing procedures to understand customer sentiment, identify trends in social media data, and extract information from documents. Image analytics<\/a> involves the process of identifying objects in digital images, classifying images, and measuring the similarity between different images. Video analytics<\/a> can also be used to track the movement of people and objects across the airport, identify key events, and measure the effectiveness of marketing campaigns. Audio analytics<\/a> can be used to identify speakers, transcribe speech, and measure the emotional tone of recorded speech. In addition, data collected from various types of sensor devices throughout the airport represent the Internet of Things that can be used to monitor equipment performance, predict failures, and optimize operations.<\/p>

Independent of the specific use case, airports of different sizes can apply the same steps for implementing data analytics<\/a> to describe and summarize the data, construct prediction models<\/a> to forecast future events, and communicate insights from the data for informed decision-making. As complex organizations, airports have data needs and use analytics<\/a> methods that will change and evolve over time. Airports can benefit from becoming more data-driven organizations as they deploy sophisticated analytical strategies and methods according to their needs and resources.<\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t

\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tData Integration and Storage<\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t

Airports collect very large amounts of data from a variety of sources across the organization, including passenger information and operational data from divisions such as transportation, security, operations, and concessions (see Table 1). Airport divisions also report budget statistics and financial data on a weekly basis that may be stored as separate spreadsheets. The information collected can be numerical, text data, video data, or social media data that is represented in different file formats. Integrating data from different sources, in various file formats, is time consuming but can be automated to some degree. The San Antonio International Airport Analytics<\/a> Team is planning to develop an Airport Information Management System that would allow division managers to input data directly into a central reporting system rather than submitting data as separate Excel spreadsheets for analysis. The data resources are processed and entered into a central data warehouse<\/a> or data lake<\/a>. Des Moines International Airport is implementing an operational database to combine multiple data resources in a central repository. For example, the airport operational database is the central database or repository for all operational systems and provides flight-related data accurately and efficiently in a real-time environment. The data warehouse<\/a> or data lake<\/a> can be queried by members of the analytics<\/a> or IT team to obtain information needed for further analysis.<\/p>

Table 1<\/span><\/b>. Example <\/span>Data Sources and <\/span>Key Performance Indicators<\/span> Generated by Airports<\/span><\/span><\/strong><\/span><\/p>

\"Table<\/a><\/p>

 <\/p>

 <\/p>

 <\/p>

 <\/p>

 <\/p>

 <\/p>

 <\/p>

 <\/p>

Note: The content and figures of the WebResource can be viewed optimally using Chrome, Edge, or Firefox browsers.<\/em><\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t

\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tKey Performance Indicators <\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t

Developing key performance indicators (KPIs)<\/a> is <\/span>an <\/span>initial<\/span> step in the analytics<\/a> process for <\/span>identifying<\/span> important <\/span>metrics for analysis. <\/span>At many airports, the analytics<\/a> team is responsible for tracking and compiling statistics about target <\/span>data<\/span> across airport divisions on a regular basis.<\/span> As part of their strategic business plan, senior leaders at Phoenix Sky Harbor International Airport (PHX) call on airport division managers annually to <\/span>identify<\/span> operational or tactical projects with a focus on capital. Measuring and tracking progress on these projects was <\/span>central<\/span> in<\/span> developing the KPIs needed to enhance operational efficiency at the airport. The PHX data analytics<\/a> team reports to the director of finance (chief financial officer) and works closely with the IT department<\/span><\/span> to <\/span><\/span>track 85 KPIs—with 25 vital statistics for financial reporting—including data on parking, revenue, customer service, rental cars, ride sharing (e.g., Uber), <\/span>aircraft<\/span> operations, and mask compliance (during the COVID-19 pandemic). Since 2017, PHX has also conducted 25,000 passenger surveys with departing passengers<\/span> each year <\/span>to <\/span>collect<\/span> data on customer demographics, travel habits, spending, and parking. <\/span>Leadership and division managers track KPIs across the airport on a weekly or monthly basis to evaluate progress toward target goals.<\/span> Targets for the KPIs are revised at the start of the year, with KPIs added and removed as needed, based on a continuing review. <\/span><\/span> <\/span> <\/span><\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t

\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tDescriptive Analytics<\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t

Descriptive analytics<\/a> involves <\/span>the process of <\/span>aggregat<\/span>ing<\/span> and <\/span>summariz<\/span>ing<\/span> data<\/span> to communicat<\/span>e insights<\/span> to <\/span>internal stakeholders and end users across <\/span>the <\/span>airport <\/span>with<\/span> visualizations and reporting dashboards<\/a>. <\/span>Reporting d<\/span>ashboards <\/span>provide<\/span> screen<\/span>–<\/span>readable summaries <\/span>that<\/span> visually display key performance indicators (KPIs)<\/a><\/span> as<\/span> charts, scales, and <\/span>metrics;<\/span> readable at-a-glance,<\/span> t<\/span>o<\/span> indicate<\/span> progress toward predefined goals<\/span>.<\/span> B<\/span>asic descriptive analytics<\/a><\/span>,<\/span> data visualization<\/a><\/span>s,<\/span> and reporting <\/span>do<\/span> not <\/span>necessarily <\/span>require a large <\/span>initial<\/span> investment or <\/span>sophisticated<\/span> analytics<\/a> <\/span>technology<\/span>. <\/span>Early in their analytics<\/a> journey, a<\/span>irports<\/span> can<\/span> s<\/span>tart<\/span> at a<\/span> small<\/span> scale<\/span> by<\/span> using existing platforms for visualization and reporting <\/span>(e.g., Excel spreadsheets) <\/span>and<\/span> then <\/span>build<\/span>ing<\/span> up <\/span>their analytics<\/a> capabilities over time<\/span>.<\/span> The <\/span>Customer Journey <\/span>Scorecard is a<\/span>n innovative<\/span> digital <\/span>platform<\/span> developed by<\/span> the Houston Airport <\/span>System<\/span> for reporting <\/span>information about<\/span> eight KPIs <\/span>internally in near real time <\/span>(i.<\/span>e., <\/span>restroom cleanliness, wait times, <\/span>c<\/span>ustoms <\/span>and <\/span>b<\/span>order <\/span>processing<\/span>,<\/span> traffic, Wi-Fi connectivity, escalator<\/span> use<\/span>, water pressure, temperature<\/span>)<\/span>.<\/span> The scorecard provided managers and employees with feedback to enha<\/span>nce operations i<\/span>n key<\/span> areas <\/span>im<\/span>pact<\/span>ing<\/span> the passenger experience.<\/span> More complex <\/span>reporting systems<\/span> can be developed according to the <\/span>airport<\/span>’s<\/span> needs and resources.<\/span> For example, <\/span>Dublin Airport<\/span> <\/span>constructed a suite of reporting dashboards<\/a> to <\/span>provide<\/span> visibility on monthly and<\/span> annual<\/span> trends in airline performance for route analysis, punctuality, load factors, <\/span>aircraft<\/span> analysis<\/span>,<\/span> and throughput<\/a><\/span> (Mullan 2019)<\/span>.<\/span><\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t

\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tPredictive Analytics<\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t

Predictive analytics<\/a> is a process of developing statistical and computational models to forecast a target outcome based on historical data. Commonly used predictive analytics<\/a> methods include time series forecasting<\/a>, linear regression, and multivariate analysis. Airports can utilize predictive analytics<\/a> models to optimize operations, improve customer satisfaction, and enhance the safety of passengers and employees. For example, a prediction model can forecast passenger demand at the airport at a given time of day based on roadway traffic, parking sales, shuttle buses, or number of bags checked. Machine learning (ML)<\/a> describes a set of advanced analytics<\/a> techniques that use statistical or computational algorithms to discover insights and make predictions from data. Unsupervised clustering models are used to group individual observations by their associations to nearby data points (e.g., k-means clustering). In terms of marketing, airports can cluster travelers by their use of products and services (e.g., retail vendors, Wi-Fi usage) and identify potential customers by the similarity of their purchases or other characteristics. By contrast, supervised classification models<\/a> are trained on existing labeled data points and then used to assign new cases to predetermined categories (e.g., logistic regression, supporting vector machines, random forests). The John F. Kennedy International Air Terminal worked with an analytics<\/a> consulting team to develop passenger profiles based on the finding that travelers arriving for very early morning flights showed a different presentation profile at security checkpoints than travelers arriving for flights later in the day. Computationally complex artificial intelligence (AI)<\/a> algorithms, such as deep learning neural networks, can provide high performance analytic solutions. A limitation of deep learning AI models is that the algorithms are not transparent to interpretation. Airports can stay competitive by leveraging the power of ML approaches, although additional development and outreach is necessary for AI systems to become more widely integrated into day-to-day operations.<\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t

\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tPrescriptive Analytics<\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t

P<\/span>rescriptive analytics<\/a><\/span> is <\/span>a<\/span> process that <\/span>exten<\/span>ds <\/span>the steps<\/span> of<\/span> descriptive and predictive analy<\/span>sis<\/span>, <\/span>going beyond the questions of<\/span> “W<\/span>hat happened in the past<\/span>?”<\/span> and<\/span> “W<\/span>hat is likely to happen in the future<\/span>?<\/span>”<\/span> to <\/span>provide<\/span> recommend<\/span>ations about<\/span> actions <\/span>for<\/span> address<\/span>ing<\/span> business<\/span> problem<\/span>s<\/span> in real time<\/span>. <\/span>Typical methods for prescriptive analytics<\/a> include the use of rule-based systems, heuristics, and model optimization.<\/span> The information from descriptive analysis<\/span> and <\/span>prediction models<\/a><\/span> provides<\/span> input <\/span>for<\/span> prescriptive analytics<\/a> to support data-based <\/span>decision-<\/span>making<\/span> and <\/span>achieve <\/span>key<\/span> business <\/span>objectives<\/span>.<\/span> For example, <\/span>prediction models<\/a> <\/span>about<\/span> peak times<\/span> in<\/span> passenger <\/span>volume at security checkpoints<\/span> provide<\/span> recommendation<\/span>s<\/span> to Transportation Security Administration<\/span> <\/span>personnel<\/span> about opening<\/span> additional<\/span> security lanes <\/span>or<\/span> making <\/span>scheduling <\/span>decisions <\/span>about<\/span> staffing<\/span> needs<\/span> to meet increased demand<\/span>.<\/span> D<\/span>ecisions<\/span> based <\/span>on <\/span>prescriptive analysis can <\/span>increase efficiency and reduce airport <\/span>costs over time.<\/span> Prescriptive analytics<\/a> can also <\/span>provide<\/span> data that<\/span> inform<\/span>s<\/span> the <\/span>planning and development of new projects at <\/span>an<\/span> airport<\/span>. <\/span>For example, Phoenix Sky Harbor International Airport<\/span><\/span> analyz<\/span>ed<\/span> passenger survey data<\/span> to <\/span>identify<\/span> factors <\/span>influencing passenger <\/span>wait times for airport buses <\/span>and<\/span> shuttles<\/span>. The results of the analysis<\/span> yielded data that led<\/span> the airport <\/span>to <\/span>extend <\/span>its<\/span> sky tram service to the car rental area<\/span>.<\/span><\/p><\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t\t\t

\n\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t<\/i><\/span>\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\t\t\t\tExample Analytics Solutions in Use<\/a>\n\t\t\t\t\t<\/div>\n\t\t\t\t\t

The use cases in this section provide examples of analytics<\/a> solutions that were implemented by airports interviewed for the case studies to address business problems encountered by passengers in their journey through the airport. Additional descriptions and details are provided in the Case Studies section.<\/span><\/p>

Customer Journey Scorecard: Digital Airport Platform<\/span> <\/span><\/strong><\/p>

The Houston Airport System (HAS) developed a Customer Journey Scorecard as <\/span>a <\/span>digital platform for <\/span>internall<\/span>y<\/span> report<\/span>ing<\/span> feedback about<\/span> current<\/span> c<\/span>onditions<\/span> at<\/span> the airport. <\/span>The concept combines a business <\/span>component<\/span> for scoring<\/span> performance on foundational passenger<\/span> needs with data and analytics<\/a> technical architecture<\/a> for implementing the platform in Power BI. The scorecard provides descriptive analytics<\/a> and data visualization<\/a><\/span>s<\/span> on eight <\/span>operational key performance indicators (<\/span>KPIs) that <\/span>are being<\/span> track<\/span>ed<\/span> and managed globally: r<\/span>oadway t<\/span>raffic, wait time<\/span>s for Transportation Security Administration (<\/span>TSA) <\/span>checkpoints across all terminals (with a goal of 22 minutes<\/span> or less<\/span>)<\/span>, <\/span>customs and border<\/span> patrol <\/span>p<\/span>rocessing, restroom<\/span> cleanliness<\/span>, <\/span>W<\/span>i<\/span>-F<\/span>i<\/span> connectivity<\/span> across terminals<\/span>, escalator<\/span> usage<\/span>, water pressure, and terminal temperature.<\/span> HAS uses Smart Restrooms <\/span>where<\/span> cleanliness <\/span>is tracked<\/span> by customer sentiment ratings registered on an iPad (i.e., happy face\/sad face) as passengers exit the restroom. A data snapshot is taken every 15 minutes to <\/span>determine<\/span> whether restroom cleanliness is above or below expectations, <\/span>identify<\/span> any <\/span>issues <\/span>for<\/span> attention (e.g., “wet floor”), and <\/span>monitor <\/span>cleaning frequency. The scorecard gives frontline employees feedback on <\/span>perform<\/span>ance<\/span> in near real time and <\/span>provides<\/span> a line of sight from their activities to the passenger experience<\/span>, to<\/span> reinforce<\/span> a sense of ownership and engagement. <\/span>The idea for the scorecard <\/span>received<\/span> widespread support across <\/span>relevant stakeholders. <\/span>Coordination <\/span>among senior<\/span> leaders, <\/span>managers<\/span>, and the <\/span>IT<\/span> team converged to <\/span>implement<\/span> the project<\/span>. <\/span>In addition,<\/span> HA<\/span>S <\/span>adopted a policy of<\/span> terminal management, <\/span>with<\/span> a<\/span> separate manager responsible for different operations <\/span>in each terminal <\/span>(e.g., custodial service, customer experience).<\/span> T<\/span>he Chief Technology Officer<\/span> was enthusiastic about the project <\/span>feasibility<\/span> and the D<\/span>ata and <\/span>A<\/span>pplications team pull<\/span>ed<\/span> the data together to<\/span> better <\/span>understand<\/span> the passenger journey.<\/span><\/span><\/span><\/p>

Key Takeaways<\/em><\/strong><\/p>