Vinyl records have re-emerged as the preferred format for music fans and artists alike. The problem is that producing vinyl records is slow and expensive; this makes it difficult for up-and-coming artists to release their music on vinyl. What if you could make your own records at home?

This thesis analyses the factors influencing the purchase of vinyl records by the members of generation Y in Sweden. Two interviews with local stores owners as well as a survey were perfomed in this regard.

La Rana Discos es una empresa dedicada a la venta de discos de vinilo, exclusivamente a través de redes sociales, la cual, al haberse incrementado el uso de las mismas como consecuencia de la coyuntura que hemos vivido por el COVID-19, tanto Facebook e Instagram se han convertido en uno de los mejores medios para ofrecer productos y servicios por el alcance que tiene a diferentes grupos de personas. En ese aspecto, La Rana Discos ofrecerá nuevos lanzamientos musicales, álbumes remasterizados, así como vinilos de época (usados) a través de sus dos canales exclusivos de venta que son Instagram y Facebook; teniendo como público objetivo a los coleccionistas de discos de vinilo o los amantes de la música (melónamos) que aprecian el sonido análogo que solo se puede apreciar a través de un LP. Del mismo modo, con el retorno de la moda retro o vintage, la industria musical ha retomado la producción de discos de vinilo e incluso se ha vuelto un pasatiempo para algunos coleccionistas conseguir discos originales de época, lo que hace un nicho de mercado interesante por el valor de estos en el mercado. A fin de diferenciarnos de la competencia, tendremos precios competitivos además de una buena atención, en la que, podremos conseguir discos a pedido, lo que nos permitirá generar fidelidad con nuestros clientes y obtener mayores seguidores en nuestras redes y de esta manera poder llegar a un mayor número de clientes. / La Rana Discos is a company dedicated to the sale of vinyl records, exclusively through social networks, which, having increased the use of them as a result of the situation that we have lived through COVID-19, both Facebook and Instagram has become one of the best means to offer products and services due to the reach it has to different groups of people. In this regard, La Rana Discos will offer new musical releases, remastered albums, as well as vintage vinyl (used) through its two exclusive sales channels, which are Instagram and Facebook; targeting vinyl record collectors or music lovers (melons) who appreciate the analog sound that can only be appreciated through an LP. In the same way, with the return of retro or vintage fashion, the music industry has resumed the production of vinyl records and it has even become a hobby for some collectors to get original vintage records, which makes an interesting market niche for the value of these in the market. In order to differentiate ourselves from the competition, we will have competitive prices as well as good service, in which we will be able to get discs on demand, which will allow us to generate loyalty with our clients and obtain greater followers in our networks and in this way be able to reach a greater number of clients. / Trabajo de investigación

Machine learning algorithms have been used for price prediction within several application areas. Examples include real estate, the stock market, tourist accommodation, electricity, art, cryptocurrencies, and fine wine. Common approaches in studies are to evaluate the accuracy of predictions and compare different algorithms, such as Linear Regression or Neural Networks. There is a thriving global second-hand market for vinyl records, but the research of price prediction within the area is very limited. The purpose of this project was to expand on existing knowledge within price prediction in general to evaluate some aspects of price prediction of vinyl records. That included investigating the possible level of accuracy and comparing the efficiency of algorithms. A dataset of 37000 samples of vinyl records was created with data from the Discogs website, and multiple machine learning algorithms were utilized in a controlled experiment. Among the conclusions drawn from the results was that the Random Forest algorithm generally generated the strongest results, that results can vary substantially between different artists or genres, and that a large part of the predictions had a good accuracy level, but that a relatively small amount of large errors had a considerable effect on the general results.