Lending startups such as ZestFinance and LendUp are putting a high-tech spin on credit scoring. ZestFinance collects as many as 10,000 pieces of data about the poor and unbanked, then lends them money at rates as high as 390 percent. In comparison, FICO scores use just a few dozen pieces of data. ZestFinance’s machines organize facts about a loan applicant into “metavariables.” Some metavariables can be expressed only as mathematical equations. Others rank applicants in categories. An applicant whose stated income exceeds that of peers flunks the veracity test. A person who moves residences too often is considered unstable. Since 2011, ZestFinance has attracted $62 million in venture financing.