OverviewThe purpose of this research study is to quantify new, commercially successful methods used in modem production and songwriting so that they can be applied and disseminated in the classroom setting.This paper will examine some of the common factors that are shared between successful songs released by Billboard Hot 100 artists over an eighteen-month period. Thus, by applying statistical analysis to a number of metrics including tempo, form, pronouns, introduction length, song length, archetypes, subject matter, and repetition of title, we can guide our students to focus their efforts toward a more commercially appealing result.The results of this research can also be used by working producers and songwriters to improve or update their craft. Unsigned bands and artists can use the information to mold and choose songs that have a greater chance of commercial success. Additionally, artist managers, A&R, and radio can use the results of this analysis to determine the viability of their artists' existing songs as hits in the current market.Review of LiteratureAs long as there has been popular music, there have been authors writing about the anatomy of pop songs and how to write a for the popular market. However, hit song science, an application of computers and statistics, is a relatively recent development. Several companies and research labs have created programs to address the subject. Most developments have occurred within the fields of informatics, data mining, and computer science.First Commercial Applications of Hit Song SciencePolyphonic HMI (Human Media Interface), a subsidiary of Grupo AIA, introduced the concept of the hit song science computer program in 2003. The company claimed that machine learning could create a profile to predict hit songs from its audio features (Elberse 2006).HMI's program used a process called spectral de-convolution, which analyzes over 25 characteristics from a dataset of over 3.5 million past commercial hits since the 1950s. This includes beat, chord progression, duration, fullness of sound, harmony, melody, octave, pitch, rhythm, sonic brilliance, and tempo. Based on its characteristics, each song was then mapped onto a multidimensional scatter plot termed the music universe. Songs with mathematical similarities were positioned very close to one another forming clusters on the chart (Elberse 2006).HMI found that most songs that had made it to the Singles Top 40 of the Billboard Hot 100 between 1998 and 2003 formed within 50 to 60 common cluster areas. The company could then examine whether or not an unreleased song mapped with these established clusters. Mike Mc- Cready, the CEO of Polyphonic and now CEO of MusicXray, states, If a song falls within one of these clusters, we can't necessarily say that it will be a hit. We just know it has the potential. The song has to conform to a couple of other criteria in order to become a hit: it has to sound like a hit, be promoted like a hit, and be marketable. But if a song falls outside of the clusters, we know it will probably not become a (Elberse 2006).Polyphonic had initially used the technology to develop a recommendation system. The idea was to develop a device placed in stores that provided recommendations to shoppers, thereby helping retailers to increase sales. Music Intelligence Solutions was one of the first companies to spawn off from HMI's use of this technology. HMI's software can also be used as a way of recommending new to audiences by creating personalized radio stations, such as Pandora. Following HMI's lead, other services such as MusicXray, Mixcloud, Uplaya, and Band Metrics have also utilized this technology (Elberse 2006).McCready further states,Hit Song Science is to the industry what the X-ray machine was to medicine. The first time someone told a doctor he could look inside a patient's body without cutting it open, it probably sounded like science fiction too. …