2018_Mioji_Strategy_developent
- 2018.01 - 2021.05 | Mioji Travel | Data Strategy Developer
- About Mioji: An AI-driven platform specializing in global travel route planning.
- Main Responsibilities: Designed and developed pricing strategies.
Pricing Strategy Design and Development
Mioji Travel provides worldwide travel planning for clients, covering flights, hotels, and activities. The task is to set the right price for these travel plans, taking into account the individual cost of items, market comparison, and the final quotation.
I took charge of designing and implementing the pricing strategy.
The core principle behind the strategy was customer satisfaction while ensuring profitability for Mioji. The idea was to set the price slightly above the cost but below the market reference. The detailed approach was:
- Given that a product can have multiple quotations, I employed a hierarchical filtering algorithm to get the confident lower cost for the product.
- Setting a reference price from the price sources to anchor customer expectations.
- Pricing the plan, keeping in mind both the reference and cost prices.
- To ensure customer satisfaction for each item, a satisfaction function was established. Using a hill-climbing algorithm, we maximized this function to determine the pricing of each item.
During the strategy's development:
- Algorithm Development: Utilized Scipy for Agglomerative Hierarchical Clustering, tweaking inter-cluster distances for clustering to determine the most trustworthy lowest price. Developed a basic hill-climbing algorithm to attain the optimal satisfaction level and thereby the price for each product.
- Algorithm Evaluation: Set up a pricing monitoring mechanism, comparing our prices with cost and reference prices to understand the current strategy's stance. Adjusted strategy parameters based on feedback from the marketing team.
- API Development: Built an API using Flask that, upon receiving a product input, would display the pricing data on the quote page.
Itinerary Creation Strategy
- Background: After the AI designs global travel routes, there's a need for textual descriptions. We aimed to design a system that auto-generates these descriptions.
- Strategy Idea: Break down elements of the journey, consider specific combinations of elements, and use preset phrases to form articles.
- Strategy Development: Using Python, we recognized elements and patterns between them. For identified patterns, we randomly selected phrases to create articles, which were then provided to the business side.