The main idea of this project is to understand the lives of the underserved people by collecting data and extracting information about the problems in their lives and coming up with a general solution to improve their lives in atleast one way.
Cities are expanding and people are moving over to these urban areas in hope of a better life. But this is also leading to a growth of slums in these cities. Most of the residents of these slum areas are devoid of some basic facilities that have become a necessity nowadays.
Some of the problems faced by these people are unsafe and/or unhealthy homes (e.g. lack of windows, dirt floor, leaky walls and roofs), overcrowded homes, limited or no access to basic services: water, toilets, electricity, transportation; unstable homes: weak structures are often blown away or destroyed during storms and earthquakes.
The impact of this project will be large. It will help eliminate a few problems faced by the people of the underserved communities and increase their standard of living.
The plan is to break up this project into various phases and have mini-goals at each phase of the project.
- The first phase of the project is to perform a thorough research and to come up with a set of questions that will be used in the survey while collecting data in the next phase. This will involve reading and gaining knowledge and basic information about the problems faced by the slum dwellers, to locate various slums spread around the city, finding information about these clusters such as their population and accessibility, and finally developing a questionnaire. This phase will take up to a few weeks to complete and the goal at this stage is the questionnaire and vital information such as the locations of slums.
- The next phase is the most important phase out of all the phases. In this phase, the required data for the project will be collected by conducting a survey. Some biases in any survey are unavoidable and the survey, to be conducted, will aim to have minimum bias. The sampling method use will be probabilistic- more specifically, random cluster sampling method. By applying this method, there will be a surety about having representation from all the areas of the city (some slums have area-specific problems. For example, a slum in Allalasandra area in Yelahanka zone of Bengaluru adjoins a lake, and they might have problems such as flooding of water into their homes.) The data collected will be stored in a common database and will be made available for use in the next phase. Completion of this phase may take a few weeks.
- The next phase involves cleaning of data and performing exploratory data analysis (EDA). The data collected will have to be cleaned. This is because there may be some incorrect values or even missing values that may creep in due to sampling errors or simply because a few people may choose not to answer a few questions. Upon cleaning the data, the next step is to perform a basic analysis on the data to understand the structure of the data and to decide the further steps to be performed in the next phase of this project. A few days will be required to complete this phase.
- This will be followed by the next phase that will involve advanced analysis of the data based on cues gained by the previous steps. Various data science techniques and machine-learning/data-analytics algorithms will be applied to the data to extract the all-important information and will end the data science part of the project. Completion of this phase may take a few weeks.
- The next phase is the one that will lead us to a potential solution to the problem posed in this project. This phase involves using the information extracted and coming up with some solutions to help the underserved communities. A possible method that can be used, here, is brainstorming. The final step will be to try and implement the best and most viable/feasible solution.