Noise

With descriptive and predictive analytics, the data set is the foundation of the client engagement. This is what the report is based on. With the analysis there may be outliers in the data set. These may be due to errors in recording or exemplary performers.

These data points should be removed from the analysis. To include would have the distinct potential to positively or negatively skew the results, depending on the data and measurement. Removing the noise provides a truer measurement within the scope.

Sharing is Caring

Data analytics has many benefits. These allow for the analysis of big data to help others. This could be predictive (letting the consumer know the best or worst time to do something, purchase a car, or more inventory), or descriptive (what is the average length a disc drive should work). The more data that is available, the better or more focussed and applicable the analysis is. This sharing of data is helpful.

Recently there has been a court case filed against Myriad Genetics Inc. alleging they are refusing to share their data. The entity has data on persons with rare conditions. This data may help with the patient's who are not in the database with their respective treatment. The requests for data are acceptable under HIPAA. the company is claiming this is proprietary.

The data would be useful for the patient's and the future of medicine as it relates to their specific illness. It is understandable the company would want to keep the data secret, as they expended money to collect this, but this needs to be released. The analysis of the data provides indications of treatment that could save lives.

Airline Efficiency

With industries, historically there has been slim margins during certain economic times. This may be due to the forces out of the industry's control. In the alternative, the margins may be fine. With either scenario, management monitors the margins and profits. Not completing this would be a glaring oversight.

Data analytics has been applied in the airline industry to ensure the best margins possible are enjoyed by the business. Optimization modeling and analytics have been applied for this and also in the decision-making process.

For instance, fuel is a large expense for airlines, as you can imagine. The modeling was applied to fuel spot pricing. This was a complex algorithm analyzing the costs of fuel along the airplane's stops, type of the aircraft, weight ot the aircraft, cost of the extra fuel, time spent fueling, and other attributes.

This is perfectly applicable to not merely the airline industry, but nearly all.

Timelines

Timelines

            Life is ruled by deadlines. The payroll has to be entered by Friday at noon. The workers have to be back from their desks by 1pm. The quarterly reports have to be in by next Thursday.

            Data analytics is no different. Time continues to be of the essence. If there is a golf tournament at a private country club for the weekend, and the organizers need the predictive report by Wednesday, it is of no use or consequence if it is delivered after Wednesday. A Friday delivery date is of no use for the client. 

Hope for the best, plan for the worst

Hope for the best, plan for the worst

            As civilization marches on, there continues to be growth. Inclusive of this movement are the construction of buildings to dwell and work in. In certain geographic areas, this tends to be problematic. Specifically there are areas that are susceptible to disasters, be these from an earthquake, tornado, or other force out of anyone’s control.     

            To work towards a safer building people can live or work in, research has been completed focusing on the building’s reactions to these forces. Examples of these occurred in California, Oregon, and other states. The buildings constructed for this provided data from shake tests, strain gauges, and accelerometers. This mountain of data has and will continue to be analyzed along with new data. The analysis, descriptive and predictive, will indicate the safest, and most tolerant materials to build with and design. This will provide for the better, safer structures for the people to be in. 

Insurance

Insurance

            Any business or industry with data has a positive application for a data analytics. The owner or C-level may want to examine at length certain aspects of the business.

            The insurance agency is well-known for using statistics to analyze their clients who are and have purchased life insurance. There are algorithms in use that are updated regularly, based on the mortality data.

            Another aspect not explored at length normally are reviewing claims in order to flag them or not for fraudulent activity. The statistics behind this would be able to provide a baseline to work from to gauge the potential for the claim to be fraudulent. The more data involved for both examples, the greater or more robust the algorithm and analysis. In working with a motivated, focused vendor, the client will receive a greater user experience.

Hospitals

Hospitals

Big data, by definition, analyzes mass amounts of data for a particular purpose. This may be to describe or predict an event with a statistical significance. The former may be for quarterly board meetings to describe the revenue level and its changes. The latter may be used to describe when traditional disk drives fail so that they may be replaced prior to this estimated date.

            For hospitals, this is a perfect fit. The administrator is able to provide data during a presentation regarding patient count. This data may be supplemented by the further analysis capabilities provided by the big data analytics in the form of why the patient count changed. The predictive analytics would be used to note the expected level of patients at a future point in time, or other pertinent points of interest.

            Data analytics in this application can be used to maintain proper staffing levels for future periods, maintain the proper inventory control, and to analyze opportunities for efficiencies and increased patients. 

Application to the Restaurant Business

Miel, LLC

Big Data Business Analytics

Restaurants

Big data is everywhere in our environment. This is accumulated in cash registers, with ticket sellers, in servers, and elsewhere. The predictive analysis is applicable to fast-casual oriented restaurants to understand the operational data and predict aspects of their business. These restaurants are becoming more common and have been slowly eating into the revenue of their larger competitors. In 2014 the top 500 restaurant report indicated an 11% increase for the fast-casual restaurant sales.

As these have become more pertinent and a force, they have looked for towards their data for assistance with making their operations more efficient and improve performance.  As these restaurants have grown, the cost has become more affordable, bringing the services more in reach.

            The restaurants are using this to answer the “why” question. Previously they engaged in elevator analysis for their operations. They would report sales went up X% this month from last month, and compare it to last year during the same time. While this is fine, it did not provide the Why this occurred, which is more important. To make a change for efficiency or better performance this has to be known and understood.

            As applied, this has assisted with optimizing the menu, segmenting the customer base, optimizing the staff usage, improving their operations, and analyzing the work flow for the time of the day and the day of the week.

Big data has the opportunity to assist incredibly with the business. The application merely needs to be utilized.

Thank you.

Thought for the day

A statistician confidently tried to cross a river that was one meter deep on average; he drowned.  Averages are good, but need to be coupled with common sense.