How to buy a car using data: Part II — the final decision and epilogue of our adventure

Guest post by Dev Nambi

In our previous blog post we identified 27 cars based on a list of features, and then narrowed our list down to 3 based on Internet data and test drives. Now, it is time for more data!

Near death experience, Wales 1964 © by PhillipC, used under Creative Commons license.

DEEP DIVE

With a list of cars this small, we can do more in-depth research. We found out the cost of car insurance, average maintenance costs, vehicle crash ratings, accident data, and insurance data. We also tried to estimate how much each model would cost to own over 5 and 10 years.

However, the most interesting data was about crash test ratings and accident statistics. Vehicle crash-test ratings are designed to be predictive, which means they try to imitate real-world conditions. Accident data is far more interesting, because it shows what actually happened.

You're OUT, Honda Civic!
The Honda Civic accident data suggests it is less safe than a Fit or Prius. We eliminated it from our list. You can’t argue with data.

We are left with two options: the Prius and the Fit. It is time to look at specific cars for sale.

ROUND 3: SPECIFIC CARS

The Internet makes it easy to find data. In our case, we used AutoTrader.com and ToyotaCertified.com to get a list of cars within 200 miles of Seattle. We wanted to find any Prius or Fit for less than $20,000 and with under 60K miles. We found 105 cars. Now that we had data, it was time for analysis!

Analysis

Our biggest question was how to consider several variables. Which is better: a $15,000 car with 32,000 miles or a $12,000 car with 46,000 miles? What if one is a year older than the other?

The way we handled this is by focusing on the variables that mattered the most to us: price, mileage, and age. We created a “score” for each car’s variable, from 0% to 100%. 100% meant it was the best deal. 0 mean it was the worst. For example, the car with the lowest mileage had a “mileage score” of 100%.

To find a “Good Deal Score,” we weighted the different scores, and then added them. We said that price matters 50%, mileage 16.6%, age 16.6%, and warranties 16.6%.

You can see the results below. The best cars had a good deal score of over 5. You can see how the best scores are often given to cars with low mileage and a low price.

We looked at the top 2 Priuses and Fits, sorting by their Good Deal Score. We realized that the 2009 Prius for $15,000 and with 25,000 miles was what we wanted. We called the car dealer, had them email us the final price ($16.5K with sales tax and registration), and we bought the car that day. No pressure, no hassle, and we knew we got a great deal. Success!

EPILOGUE

Lessons Learned:

  • The Internet levels the playing field. A few days’ research can make you a much savvier car shopper, giving car salesmen less of an edge.
  • Remember that the buyer has all of the leverage. I can choose not to buy a car from someone at any time.
  • Make car dealers bid for your business. Use phone or email, so they can’t pressure you.

Pros:

  • Discussing features first was a brilliant idea. We both compromised to make that list of features, but in a low pressure situation. Later on, Kate & I never disagreed about whether a car was a good fit for us, because we both were looking for the same thing.
  • Decide which model(s) to buy before deciding which specific car to buy.
  • The amount of money you can save by comparison shopping is incredible. We could immediately tell whether a specific car was a good deal or not based on the data.
  • A modest amount of time = massive savings. We spent ~40 hours doing research, analysis, and test drives that may save us $5,000 to $15,000 over the life of the car. That comes out to $125 to $375 saved per hour.
  • Using data = fewer disagreements. Kate & I always agreed which car was safer, because the data told us. We knew which specific car was a better deal, because our analysis said so.

Limitations:

  • Self awareness. Why are certain features and options important to you?
  • Emotional control. It is hard to walk away from a nice car because you are not intellectually ready to buy it.
  • Takes time. Those 40 hours were not spent on sleep, reading, or blogging.

What We Wish We Had:

  • Car maintenance/reliability data. We still don’t know which car models are more reliable than others.
  • Car price predictor data. We didn’t know whether car prices were going up or down.
  • A service to do this for us. I would gladly pay $100 for some company to do all of this work, and deliver the car to my front door.

How did you make your last car purchasing decision?

Comments on How to buy a car using data: Part II — the final decision and epilogue of our adventure

  1. damn. y’all are so smart (and your charts are cool). i hated the car-buying process (and i kind of hate the car we ended up with…at least my wife loves it).

    but the real question is: now that you’ve got the process down, would you do this for someone else for $100? we’re no longer in the market, but i’d totally have paid for that!

    • Lady Brett,

      If I could find a way to pull the AutoTrader data automatically, I’d love to do this as a business. The hard part is that pulling all of that data on specific cars took about 10 hours, and it would be different depending on different models, cities, criteria. So if I couldn’t automate that, it would pay less than minimum wage.

  2. I am curious why you didn’t use consumer reports to get reliability and maintenance numbers? We always do so, and it has never steered us wrong. I didn’t do the kind of in depth analysis you guys have, but I still came up with same two models you looked at as my choices (but I’m not quite ready to buy yet!) So that makes me feel better about my choice, because let’s face it, Data is COOL AS HELL!

    I enjoyed reading about all your hard work. The uber geek in me was cackling with glee the whole time

  3. omg… I think you and my husband would be bffs because when shopping for a car last fall we made an almost identical set of spreadsheets and graphs. our most limiting factor was that I am very tall and so head/leg room was an important factor.

  4. That’s very cool and analytical of you guys. I was perplexed at the end when it seemed to be very easy to go with the lowest mileage/ newest year. I feel that’s the only thing I would’ve weighed differently. There can be huge differences from year to year and sometimes newer is not always better. The mileage thing in general is usually true with the exception of something with 20k or less. At that point the transmission hasn’t broken itself in yet and without a bulletproof warranty (non existent IMHO) I would be wary of a car THAT new. Sometimes the car with 75k miles can be better depending on its maintenance history and past issues. Another factor for me would be the advice of friends and family, especially those with mechanical expertise and if you could find someone that owns the models you are looking at, it’s surprising how problems really can run across the board for a specific model. It just goes to show that everyone has different priorities and you guys did a great job of pinpointing yours and narrowing it down.

    • Hi Megan,

      You make a great point. I looked at the data after we bought our car and asked “Why didn’t I pick the absolute best deal?”. It was mostly emotion, honestly. We liked the idea of lower environmental impact more than a slightly better deal, so we went with the Prius.

      I didn’t write about it, but we did ask various friends, coworkers and family about the cars they drove. It was great feedback, but I was worried about personal bias. We did get universal praise for the Civic, Fit and Prius, though. That was reassuring.

  5. ” What We Wish We Had: A service to do this for us. I would gladly pay $100 for some company to do all of this work, and deliver the car to my front door.”

    Well, you’ve already completed a pilot test, so why not start your own business providing this service? Whenever my car dies I’d gladly hire you – and pay more than $100 for all this research!

  6. you know, i used consumer reports the last time i bought a car. i spent less than 5 hours “virtual shopping” bc they have already collected all the data for all the years and models and conditions of used cars – including reliability. i’m sure your method worked for you and i know you’ll love your car for years to come, but consumer reports is better for the “layman” data analyst.

  7. I’m curious: did you test drive the final three models before deciding which you should buy? My man and I are a foot apart in height and I can’t imagine not test driving to see if we’re both comfortable in the car (even if we have to put up with pushy salesmen).
    Very cool analysis. Seems very similar to what I do would, except with more grafts. You are teh master of grafts!

    • We definitely did. We actually test drove the prius a couple of times at different dealerships, a friend’s ft that was the same year we were looking at, and the civic at a third dealership. We drove the Prius twice because a salesman at the first place was so irritating he made it impossible to focus on driving. Even the best data analysis can’t weed out the slimy used car salesman, I guess!

  8. I feel that I should amend this post to say that whenever Dev talks about what “we” did with the data, he’s overselling my brainiac capacities. I helped analyze the data when formatted by Dev and presented to me, but he’s definitely the data scientist that did all the genius work. I’m the biology nerd that kept saying “….but….but….but super high gas mileage!”

  9. I agree with the advantage of doing your homework online. I just bought a car last week and it definitely leveled the playing field. We were able to get the dealer we wanted to deal with to match things from two other dealerships, one in another state. It saved me $3000.

  10. I love the data you collected here and how you analyzed it – but you’re right, you can’t really know until you test drive and having long term data is also useful. I have a 2001 VW GTI that I love to bits and it hasn’t really given me any issues either, I take it in to the dealership for routine maintenance though, VW is very good to me 🙂 another couple in my building has a VW Jetta they seem very happy with, and another girl has a Honda Fit she seems pretty happy with as well (I live in a small building! We have a Civic owner too). I knew another couple who owned a Fit and they drove it across Canada, great fuel economy! My GTI is decent too, we drove it to my grandparent’s place last spring which easily a 5 hour drive away (can’t remember the exact mileage, over 500km’s I believe) and we made it on a tank of gas 🙂

  11. i’m excited about this post! my car just got totaled last week and we’ve been doing some shopping, but it hasn’t been nearly this intellectual. although i think there are some things to a good car that you can’t quite quantify. my last car made me happy to ride in, and it was perfect for kicking back and putting my feet up on the dash while the husband was driving. so now every car we’ve test driven i’ve taken my shoes off and stuck my feet up on the dash, even if the salespeople think i’m crazy. the point is… yeah, the numbers have to fit, but it’s also got to feel right. i hope you two are happy with your new ride. 🙂

  12. Are you conflating causation and correlation when excluding the Civic? Isn’t the user base for the Civic much wider than for the Prius and Fit, including more young people/new drivers and more folks who modify their cars?

    • Hi Adrianne,

      For the car accident data, I checked on that. The data is adjusted so it talks account percentages of people driving, not the number of cars. It isn’t adjusted for the type of person driving. If unsafe drivers are naturally drawn to a Civic more than a Fit, the Civic would have worse numbers. The only way I could think of to adjust for that was to call my insurance company and ask for quotes for me. The civic costs about $5 more per year to insure than the other two, for me anyway.

  13. One thing that is important to remember to consider are maintenance costs, particularly if you plan on keeping it until it dies. Hybrids in particular are pricey to fix.

Leave a Reply to Stacy Cancel reply