Hoppit

Hoppit Logo
Screen 1
Screen 2
Screen 3

Inspiration

If you were to ask someone that if they were given an opportunity to travel would they accept it? The vast majority of those would answer in the affirmative. But at the same them if you remind them that they have an entire trip to plan, you quickly see the number dwindle down due to the hassle associated with the travel. This simple hesitation sparked our biggest inspiration. The untapped market potential is what led to our interest in a product that can be monetized due to the discomfort caused by planning in the midst of something that is supposed to be a getaway from stress. On a different note, there are many individuals post retirement who have dreams to see the world and in some cases move to areas which meet their "dream home." Our scoring system uses data gathered by the HPCC data sets to create optimal travel/moving opens for these individuals.

What it does

Our goal in this project was to allow users to book a trip independently but once they reach their destination, the user input their interest and the time frame of their choice. Using those parameters our program creates an automated itinerary which suggests attractions, restaurants, events and many others personalized choices based on the input. At the same time we are able to rank these cities and locations based on the users choices before arrival to see if it as optimal fit based the datasets provided by HPCC.

How we built it

So, How’d we do it? carefully. In all seriousness, this was a massive effort that pulled together to minimal collective knowledge our group had of React Typescript, Js, Java, and a hilarious attempt at learning ECL. Our frontend is build in React, and has a tiny Flask server that serves up responses to user queries. It’s functional, mostly. The biggest issue was that we tried to use ECL the wrong way. It’s a hard language and framework to learn, especially with such limited time. Regardless, the effort was there, and we did make a lot of progress towards functionality. Part of the plan was to have a GPT3 trained chatbot that would give responses to travel related questions, too. It didn’t end up working too well, mostly because the training time for a GPT3 fine tuning is nearly 2 weeks. It was a great plan in theory, but docs and q/a support is minimal for GPT3 web integration. I’m still really proud of the work that our group did this weekend. 10/10,would do again.

Alex

Challenges we ran into

One of the major challenges we ran into was the lack of communication in the group which led to a major diversion in the development that led to the project not coming out the way we hoped. At one point we had to essentially sit everyone down and make sure we were even doing the same project. It was like a bridge being built on two sides that never connected due to miscommunication.

Accomplishments that we're proud of

We are proud of the fact that we were able to learn how to use new software and implement it in order to complete the project. At the same time we are proud to submit something that can be helpful in many ways if used and developed properly.