NBA Playoff Predictions. I toyed around with building video games, making basic websites, iOS applications, but in a way, I was spreading myself thin by not specializing in a certain craft. When I started programming a few years back, I never had a purpose for what I would use my newfound skills for. What will the players think about the NBA coming back. As we did last year, I’ve written the case for the over and under for every team’s win total and ranked whichever one I’m going with based on my confidence in the bet. If you enjoyed this article or would like to discuss any of the information mentioned, you can reach out to me on Linkedin, Twitter, or by Email. it can maybe that can replace the lottery balls. Because by superstars requesting trades or signing with other teams that are more developed. For the remainder of my prediction, I implemented a scoring method that gave me a spread that my algorithm created, based on which team was more likely to win. CBSSports.com's NBA expert picks provides daily picks against the spread and over/under for each game during the season from our resident picks guru. My next step was to merge these files into one dataset. My attempts began as follows: Out of all the models attempted, the one with the highest accuracy was the support vector machine SVC classifier, with an accuracy of 72.52% on historical data! For my first 28 game predictions, I was simply going off who was going to win, not taking into account the spread I was offered. My algorithm was typically in line with what online sports betting websites published which was a good sign. We now had to process our 2 sets of CSV files in a format where they can be compared and analyzed. This new model will be based on the players within a team as opposed to the team as a whole. Once again, I used Selenium and scraped these monthly stats tables, and saved them as CSV files. Will this break help or hurt teams (skip right to the playoffs) good teams. I also wanted to attempt a financial strategy and began by simply betting on the predicted winner. I also decided to limit my search to data beginning from the 2008–2009 season to the present. For the data acquisition portion of this project, I used Selenium, a python package that facilitates web scraping, to get the data I needed off various websites. This could move all stars and make free agency more interesting. The NBA, as well as many other sports, has seen the use of statistics exponentially grow over the last 10–20 years. Although we do see some features with greater importance, we don’t have a clear reason to eliminate any features at this point, but it allows for some interesting observations to be made. All Machine Learning Algorithms You Should Know in 2021, 5 Reasons You Don’t Need to Learn Machine Learning, Object Oriented Programming Explained Simply for Data Scientists. A friend of mine introduced me to a great python package called Speedml which simplifies the process of exploratory analysis and produces great looking plots to share your data. On the first day of running my model, in 5 out of 7 games the underdog won the match. My NBA Standings prediction for 2020-2021 I based this off how good and young all the players are, and the teams short and long term success. Hands-on real-world examples, research, tutorials, and cutting-edge techniques delivered Monday to Thursday. Take a look, I created my own YouTube algorithm (to stop me wasting time). Immediately we can tell that selectiveness is a better strategy, which involves choosing the more favorable odds. Yes I think that the seeds don't matter because looking at the proposed playoff format I can see a lot of times that the lower seed wins against a higher seed, example: An example of the lower seed beating the higher seed is Luka and the Mavericks beating Chris Paul and the OKC thunder, PREDICTION: I think that the finals will be Bucks Lakers and the Lakers would win in six, Will the break affect rosters and the NBA season's going forward. Wild prediction: The Oklahoma City Thunder, after trading away both Russell Westbrook and Paul George, will finish within five wins of last year’s total of 49. My data source for the past results was Basketball-Reference.com, which had match results going back to 1946. When you have numerical features, it is always interesting to see how each feature in our dataset correlates to the other. I also needed to know what every team’s stats were for any given month, and my data source for this was the official NBA Stats page. Don’t Learn Machine Learning. NBA Playoff Predictor (NBA Season Picker) lets you pick every game of the NBA Season via a season Schedule Most teams want to come back and the players want to come back because they want something to do. The next step was figuring out how to acquire this data. Using Selenium, I scraped these tables one-by-one and converted them to CSV files for later use. As we can see from the data below, there has been no clear advantage for teams playing across a range of situations since the 2007 season.