Adam Fletcher

Consultant Data Scientist @Equal Experts

Predicting the price of assets at auction- The client wanted to determine factors that influenced the price of assets at auctioned to better list assets- I developed dashboards to drill into the factors that influence asset price over time in Power BI and a dashboard that interacts with a random forest model to predict the current asset price at various auction locations- The business is now able to sell assets faster and at a more appropriate price. They are also able to predict depreciation price on new assets and factor the price of selling assets in project costings. Creating needs-based personas for a job-listing service- The client wanted to better understand how users interacted with a job-listing website, with the aim of personalising user experiences based upon a set of needs they might have- Working with a UX company we conducted interviews and designed surveys to gather information about what needs users were experiencing when applying for a job (roughly respondents)- The dataset was incomplete to avoid asking respondents too many questions, so Boolean matrix-factorisation was employed to predict user responses for unasked questions, followed by clustering to group users with similar needs- The clusters were converted into personas with user stories and the business was now better able to respond to the user’s needs, improving user retention and paid user numbers. Modelling the cost of debt for delayed payment terms in commercial projects- The client wanted to understand how the debt resulting from delayed payments terms affected the net cost of a project it affects company liquidity- Using incoming and outgoing costs for each project I created a mixed-phase model for running projects, including the amount of debt accrued and how increased payment terms affected debt the cost of credit- With this information, the client restructured their pricing system and was better able to forecast their liquidity at key times of the year